Enhancing automatic term recognition through recognition of variation  
Goran Nenadić
*
  
Department of Computation 
UMIST 
Manchester, UK, M60 1QD 
G.Nenadic@umist.ac.uk 
Sophia Ananiadou
*
 
Computer Science 
University of Salford 
Salford, UK, M5 4WT  
S.Ananiadou@salford.ac.uk 
John McNaught
*
 
Department of Computation 
UMIST 
Manchester, UK, M60 1QD 
J.McNaught@umist.ac.uk 
 
                                                      
*
 Co-affiliation: National Centre for Text Mining, Manchester, UK 
Abstract 
Terminological variation is an integral part of the 
linguistic ability to realise a concept in many ways, 
but it is typically considered an obstacle to 
automatic term recognition (ATR) and term 
management. We present a method that integrates 
term variation in a hybrid ATR approach, in which 
term candidates are recognised by a set of 
linguistic filters and termhood assignment is based 
on joint frequency of occurrence of all term 
variants. We evaluate the effectiveness of 
incorporating specific types of term variation by 
comparing it to the performance of a baseline 
method that treats term variants as separate terms. 
We show that ATR precision is enhanced by 
considering joint termhoods of all term variants, 
while recall benefits by the introduction of new 
candidates through consideration of different 
variation types. On a biomedical test corpus we 
show that precision can be increased by 20–70% 
for the top ranked terms, while recall improves 
generally by 2–25%. 
1 Introduction 
Terminological processing has long been 
recognised as one of the crucial aspects of 
systematic knowledge acquisition and of many 
NLP applications (IR, IE, corpus querying, etc.). 
However, term variation has been under-discussed 
and is rarely accounted for in such applications.  
When naming a new concept, scientists and 
specialists usually follow some predefined term 
formation patterns, a process which does not 
exclude the usage of term variations or alternative 
names for concepts. Term variations are very 
frequent: approximately one third of term 
occurrences are variants (Jacquemin, 2001). They 
occur not only in text, but also in controlled, 
manually curated terminological resources (e.g. 
UMLS (NLM, 2004)).  
The task of an automatic term recognition (ATR) 
system is not only to suggest the most likely 
candidate terms from text, but also to correlate 
them with synonymous term variants. In this paper, 
we briefly present an analysis of term variation 
phenomena, whose results are subsequently 
incorporated into a corpus-based ATR method in 
order to enhance its performance.  
The paper is organised as follows. In Section 2, 
we analyse the main types of term variation, and 
briefly examine how existing ATR systems treat 
them. Our approach to incorporating variants into 
ATR is presented in Section 3. In Section 4, we 
evaluate our approach by comparing it to a 
baseline method (the method without variation re-
cognition), and we conclude the paper in Section 5. 
2 Background 
Terms are linguistic units that are assigned to 
concepts and used by domain specialists to 
describe and refer to specific concepts in a domain. 
In this sense, terms are preferred designators of 
concepts. In text, however, concepts are frequently 
denoted by different surface realisations of 
preferred terms, which we denote as their term 
variants. Consequently, a concept can be 
linguistically represented using any of the surface 
forms that are variants of the corresponding 
preferred term. We consider the following types of 
term variation: 
 
(i) orthographic: e.g. usage of hyphens and slashes 
(amino acid and amino-acid), lower and upper 
cases (NF-KB and NF-kb), spelling variations 
(tumour and tumor), different Latin/Greek 
transcriptions (oestrogen and estrogen), etc. 
(ii) morphological: the simplest variations are 
related to inflectional phenomena (e.g. singular, 
plural). Derivational transformations can lead to 
variants in some cases (cellular gene and cell 
gene), but not always (activated factor vs. 
activating factor); 
(iii) lexical: genuine lexical synonyms, which may 
be interchangeably used (carcinoma and 
cancer, haemorrhage and blood loss); 
(iv) structural: e.g. possessive usage of nouns 
using prepositions (clones of human and human 
clones), prepositional variants (cell in blood, 
cell from blood), term coordinations (adrenal 
glands and gonads); 
(v) acronyms and abbreviations: very frequent 
term variation phenomena in technical 
sublanguages, especially in biomedicine; 
sometimes they may be even preferred terms 
(DNA for deoxyribonucleic acid).  
 
Note that variation types (i) – (iii) affect 
individual constituents, while (iv) and (v) involve 
variation in structure of the preferred term. In any 
case, they do not “change” the meaning as they 
refer to the same concept. Daille et al. (1996) and 
Jacquemin (1999, 2001) further identified types of 
variation that modified the meaning of terms.  
Although many authors mention the problems 
related to term variation, few have dealt with 
linking the corresponding term variants. Also, the 
recognition of variants is typically performed as a 
separate operation, and not as part of ATR.  
The simplest technique to handle some types of 
term variation (e.g. morphological) is based on 
stemming: if two term forms share a stemmed 
representation, they are considered as mutual 
variants (Jacquemin and Tzoukermann, 1999; 
Ananiadou et al., 2000). However, stemming may 
result in ambiguous denotations related to “over-
stemming” (i.e. resulting in the conflation of terms 
which are not real variants) and “under-stemming” 
(i.e. resulting in the failure to link real term 
variants).  
Other approaches to the recognition of term 
variants use preferred terms and known synonyms 
from existing term dictionaries and approximate 
string matching techniques to link or generate 
different term variants (Krauthammer et al., 2001; 
Tsuruoka and Tsujii, 2003).  
Jacquemin (2001) presents a rule-based system, 
FASTR, which supports several hundred meta-
rules dealing with morphological, syntactic (i.e. 
structural) and semantic term variation. Term 
variation recognition is based on the 
transformation of basic term structures into variant 
structures. However, the variants recognised by 
FASTR are more conceptual variants than 
terminological ones, as non-terminological units 
(such as verb phrases, extended insertions, etc.) are 
also linked to terms in order to improve indexing 
and retrieval.   
 
3 Incorporating term variation into ATR 
Our approach to ATR combines the C-value 
method (Frantzi et al., 2000) with the recognition 
of term variation, which is incorporated as an 
integral part of the term extraction process.  
C-value is a hybrid approach combining term 
formation patterns with corpus-based statistical 
measures. Term formation patterns act as linguistic 
filters to a POS tagged corpus: filtered sequences 
are considered as potential realisations of domain 
concepts (term candidates). They are subsequently 
assigned termhoods (i.e. likelihood to represent 
terms) according to a statistical measure. The 
measure amalgamates four corpus-based 
characteristics of a term candidate, namely its 
frequency of occurrence, its frequency of 
occurrence as a form nested within other candidate 
terms, the number of candidate terms inside which 
it is nested, and the number of words it contains.   
The original C-value method treats term variants 
that correspond to the same concept as separate 
term candidates. Consequently, by providing 
separate frequencies of occurrence for individual 
variants instead of a single frequency of 
occurrence calculated for a term candidate unifying 
all variants, the corpus-based measures and 
termhoods are distributed across different variants. 
Therefore, we aim at enhancing the statistical 
evaluation of termhoods through conflation of 
different surface representations of a given term, 
and through joint frequencies of occurrence of all 
equivalent surface forms that correspond to a 
single concept.  
In order to conflate equivalent surface 
expressions, we carry out linguistic normalisation 
of individual term candidates (see examples in 
Table 1). Firstly, each term candidate is mapped to 
a specific canonical representative (CR) by 
semantically isomorphic transformations. Then, we 
establish an equivalence relation, where two term 
candidates are related iff they share the same CR. 
The partitions of this relation are denoted as 
synterms: a synterm contains surface term 
representations sharing the same CR.  
 
synterm 
canonical 
representative 
human cancers 
cancer in humans 
human’s cancer 
human carcinoma
}
human cancer 
Table 1: Term normalisation examples 
 
Our aim is to form synterms prior to the syntactic 
estimation of termhoods for term candidates. 
Therefore, after the extraction of individual term 
candidates, we subsequently normalise them in 
order to generate synterms, where the 
normalisation is performed according to the 
typology of variations described in Section 2. More 
precisely, we consider separately the normalisation 
of variations that affect term candidate constituents 
and variations that involve structural changes. The 
general architecture of our ATR approach is 
presented in Figure 1. 
 
 
POS tagger 
 
Inflectional normalisation 
Structural  normalisation 
Orthographic normalisation 
Extracted synterms 
Input documents 
Termhood estimation 
Extraction of term candidates 
Acronym acquisition 
 
Figure 1: The architecture of the ATR process 
 
3.1 Normalising term constituent variation 
In the case of variations that do not affect the 
structure of terms, the formation of CRs is based 
on a POS tagger (for inflectional variation) and 
simple heuristics (for orthographic normalisation). 
For example, different transcriptions of 
neoclassical combining forms are treated by 
replacements of specific character combinations 
(ae → e, ph → f) in such forms (and only in such 
forms). Inflectional normalisation is based on POS 
tagging: a canonical term candidate form is a 
singular form containing no possessives (Down’s 
syndrome → down syndrome). 
In order to address lexical variants, one can use 
dictionaries of synonyms where the preferred terms 
are used for normalisation purposes ({hepatic 
microsomes, liver microsomes} → liver 
microsomes). In experiments reported here, we did 
not attempt to normalise lexical variation. 
 
3.2 Normalising term structure variation 
Variations affecting term structure are less frequent 
but more complex. Here we consider two types of 
term variation: prepositional term candidates and 
coordinated term candidates (for a detailed analysis 
of these variations see (Nenadic et al., 2004)). 
Prepositional term candidates are normalised by 
transformation into corresponding expressions 
without prepositions. Using prepositions of, in, for 
and by as anchors, we generate semantically 
isomorphic CRs by inversion. For example, the 
candidate nuclear factor of activated T cell is 
transformed into activated T cell nuclear factor. 
Here is a simplified example of a rule describing 
the transformation of a term candidate that 
contains the preposition of: 
 
if  structure of  term candidate is   
   (A|N)
1
* N
1
 Prep(of) (A|N)
2
* N
2
  
then   CR = (A|N)
2
* N
2
 (A|N)
1
* N
1 
 
In order to address the problems of determining 
the boundaries of term constituents in text (to the 
right and left of prepositions), for each 
prepositional term candidate we generate all 
possible nested candidates
†
 and their corresponding 
CRs. For example, for the candidate regulation of 
gene expression, we generate both gene regulation 
and gene expression regulation. Since this 
approach also generates a number of false 
candidates, additional heuristics are used to 
enhance precision, such as removing adverbials 
and determiners, using a stop list of 
terminologically irrelevant prepositional 
expressions (e.g. number of ..., list of ..., case of ..., 
in presence of ...), etc.  
A similar approach is used for the recognition of 
coordinated term candidates: coordinating 
conjunctions (and, or, but not, as well as, etc.) are 
used as anchors, and when a coordinating structure 
is recognised in text, the corresponding CRs of the 
candidate terms involved are generated.  
We differentiate between head coordination 
(where term heads are coordinated, e.g. adrenal 
glands and gonads) and argument coordination 
(where term arguments/modifiers are coordinated, 
e.g. SMRT and Trip-1 mRNAs). 
The recognition and extraction of coordinated 
terms is highly ambiguous even for human 
specialists, since coordinated terms and term 
conjunctions share the same structures (see Table 
2). Also, similar patterns cover both argument and 
head coordinations, which makes it difficult to 
extract coordinated constituents (i.e. terms). Not 
only is the recognition of term coordinations and 
their subtypes ambiguous, but also internal 
boundaries of coordinated terms are blurred. In a 
separate study, we have shown that 
morphosyntactic features are insufficient both for 
the successful recognition of coordinations and for 
the extraction of coordinated terms: in many cases, 
the correct interpretation and decoding of term 
coordinations is only possible with sufficient 
background knowledge (Nenadic et al., 2004). 
                                                      
†
 Each constituent extracted from a nested pre-
positional term candidate has to follow a pattern used 
for the extraction of individual candidate terms. 
 
example adrenal  glands and gonads 
head 
coordination 
[adrenal [glands and gonads]] 
term  
conjunction  
[adrenal glands] and [gonads] 
Table 2: Ambiguities within coordinated structures 
In order to address the problems of structural 
ambiguities and boundaries of coordinated terms, 
we also generate all possible nested coordination 
expressions and corresponding term candidates. 
For example, from a candidate coordination viral 
gene expression and replication we generate two 
pairs of coordinated term candidates: 
 
viral gene expression  and  viral gene replication 
viral gene expression  and  viral replication 
 
Patterns for the extraction of term candidates 
from coordinations have been acquired semi-
manually for a subset of term coordinations. For 
each pattern, we define a procedure for the 
extraction of coordinated term candidates and 
generation of the corresponding CRs (see Table 3 
for examples). The generated candidates from 
coordinated structures are subsequently treated as 
individual term candidates. 
 
3.3 Normalising acronym variation  
We treat acronym extraction as part of the ATR 
process (see Figure 1). In (Nenadic et al., 2002) we 
suggested a simple procedure for acquiring 
acronyms and their expanded forms (EFs), which 
was mainly based on using orthographic and 
syntactic features of contexts where acronyms 
were introduced. The model is based on three types 
of patterns: acronym patterns (defining common 
internal acronym structures and forms), definition 
patterns (based on syntactic patterns which 
describe typical contexts where acronyms are 
introduced in text) and matching patterns (the set 
of matching rules between acronyms and their 
corresponding EFs).  
Acronyms also exhibit variation (e.g. RAR alpha, 
RAR-alpha, RARA, RARa, RA receptor alpha etc. 
are all acronyms for retinoic acid receptor alpha). 
Therefore, in addition to extracting acronyms, we 
further gather all acronym variants and their EFs, 
and we map them into a single CR. Since in this 
paper acronyms are taken as term variants, we  
”replace” acronym occurrences by the CR of their 
EFs. In order to bypass the problem of acronym 
ambiguity, we replace/normalise only acronyms 
that are introduced in a given document. 
 
(N|A)
1
 & (N|A)
2
 (N
+
)
3
 
candidate
1
 = (N|A)
2
 (N
+
)
3
 
candidate
2
 = (N|A)
1
 nested(N
+
3 
) 
 
e.g.   B and T cell antigen    
          T cell antigen    
          B cell antigen, B antigen 
N
1
 & N
2
 A
3
 N
+
4 
candidate
1
 = N
2
 A
3
 N
+
4
 
candidate
2
 = N
1
 A
3
 N
+
4 
 
e.g.  function or surface antigenic profile 
     surface antigenic profile   
     function antigenic profile 
N
+
1
 N
2
 
& (N|A)
3 
candidate
1
 = N
+
1
 N
2
 
 
candidate
2
 = nested(N
+
1
) (N|A)
3
  
 
e.g.  breast cancer therapy and prevention 
     breast cancer therapy  
     breast caner prevention, breast  prevention 
N
+
1
 (A
+
)
2
  
A
3
 &  A
4
 
candidate
1
 = N
+
1
 (A
+
)
2 
A
3
  
candidate
2
 = N
+
1
 (A
+
)
2 
A
4
  
 
e.g.  RNA polymerases II and III 
      RNA polymerasis II 
      RNA polymerasis III 
Table 3: Examples of patterns used for the 
extraction of term candidates from coordinations  
(nested denotes the generation of all possible 
linearly nested substrings)  
3.4 Calculating termhoods with variants 
Term variants sharing the same CR are grouped 
together into synterms, and the calculation of C-
values (i.e. termhoods) is performed for the whole 
synterm rather than for individual term candidates. 
The main reason for doing this is to avoid the 
distribution of frequencies of occurrence of term 
candidates across different variants, as these 
frequencies have a significant impact on estimating 
termhoods. Instead of providing separate 
frequencies of occurrence and obtaining termhoods 
for individual term candidates, we provide a single 
frequency of occurrence and joint termhood 
calculated for a synterm, which unifies all variants. 
Similarly to the estimation of C-values for 
individual term candidates (Frantzi et al., 2000), 
the formula for calculating the termhoods for 
synterms is as follows: 
 
 





⋅
−⋅
=
∑
∈
nestednot  is CR),(||log
nested is CR,))(
||
1
)((||log
  )value(-C
2
2
CRfCR
bf
T
CRfCR
c
CR
TbCR
 
where c denotes a synterm whose elements share a 
canonical representative (denoted as CR in the 
formula), f(CR) corresponds to the cumulative 
frequency with which all term candidates from the 
synterm c occur in a given corpus, |CR| denotes 
the average length of the term candidates (the 
number of constituents), and T
CR
 is a set of all 
synterms whose CRs contain the given CR as a 
nested substring. 
This approach ensures that all term variants are 
naturally dealt with jointly, thus supporting the fact 
that they denote the same concept. As a 
consequence, we expect that precision would be 
enhanced by considering joint frequencies of 
occurrence and termhoods for all variants of 
candidate terms, while recall would benefit by the 
introduction of new candidates through 
consideration of different variation types. 
 
4 Evaluation and discussion 
In order to assess the effectiveness of incorporating 
specific types of term variation into ATR, we 
compared the performance of the baseline C-value 
method (without considering variations) with the 
approach including recognition and conflation of 
term variants. Here we are not interested in an 
absolute measure of the ATR performance, but 
rather in the comparison of results obtained 
through handling different variation types.  
We conducted two sets of experiments: in the 
first experiment, we analysed the incorporation of 
term candidates resulting from considering term 
variations individually, while, in the second, we 
experimented with the integration of combined 
variations in the ATR process. 
The evaluation was carried out using the GENIA 
corpus (GENIA, 2004), which contains 2,000 
abstracts in the biomedical domain with 76,592 
manually marked occurrences of terms. These 
occurrences (which include different term variants) 
correspond to 29,781 different, unique terms. Each 
occurrence of a term in the corpus (except 
occurrences of acronyms) is linked to the 
corresponding “normalised” term (typically a 
singular form), while coordinated terms are 
identified, marked and normalised within term 
coordinations. A third of occurrences of GENIA 
terms are affected by inflectional variations, and 
almost half of GENIA terms have inflectional 
variants appearing in the corpus. On the other 
hand, only 0.5% of terms contain a preposition, 
while 2% of all term occurrences are coordinated, 
involving 9% of distinct GENIA terms (for a 
detailed analysis of GENIA terms see (Nenadic et 
al., 2004)). 
We used the list of GENIA terms as a gold 
standard for the evaluation. Since our ATR method 
produces a ranked list of suggested synterms, we 
considered precision at fixed rank cut-offs 
(intervals): precision was calculated as the ratio 
between the number of correctly recognised terms 
and the total number of entities recognised in a 
given interval (where an interval included all terms 
from the top ranked synterms).
‡
 The baseline 
method (original C-value) was treated in the same 
way, as term candidates suggested by the original 
C-value could be seen as singleton synterms. In 
order to estimate the influence on recall, we also 
used all variants from suggested synterms.  
The incorporation of individual variations 
affecting term constituents into ATR had 
considerable positive effects, especially on the 
most frequently occurring terms (see Figures 2a 
and 2b): for some intervals, inflectional variants, 
for example, improved precision by almost 50%. 
Similarly, the integration of acronyms improved 
precision, in particular for frequent terms (up to 
70%), as acronyms are typically introduced for 
such terms. As one would expect, the combined 
constituent-level variations further improved 
interval precisions compared both to the baseline 
method and individual variations (see Figure 2c). 
However, the incorporation of structural variants 
(in particular for prepositional terms) negatively 
influenced precision compared to the baseline 
method, as many false candidates were introduced.  
In order to assess the quality of extracted 
prepositional term candidates, we evaluated a set 
of the 117 most frequently occurring candidates 
with prepositions: 80% of suggested expressions 
were deemed relevant by domain experts, although 
they were not included in the gold GENIA 
standard (such as expression of genes or binding of 
NF kappa B). Still, the recognition of prepositional 
term candidates is difficult as they are infrequent 
and there are no clear morphosyntactic cues that 
can differentiate between terminologically relevant 
and irrelevant prepositional phrases. 
The incorporation of coordinated term candidates 
had only marginal influence on precision, mainly 
because they were not frequent in the GENIA 
corpus. Furthermore, simple term conjunctions 
                                                      
‡
 It was an open question whether to count the 
recognition of each term form (e.g. singular and plural 
forms, an acronym and its EF, prepositional and non-
prepositional forms) separately (i.e. as two positive 
“hits”) or as one positive “hit” (see also (Church, 
1995)). Since the evaluation of the baseline method 
(original C-value) typically counts such hits separately, 
we decided to follow this approach, and consequently 
count all positive hits from synterms.  
 
were far more frequent than term coordinations, 
which made their extraction highly ambiguous. 
Still, using only the patterns from Table 3, we have 
correctly extracted 35.76% of all GENIA 
coordinated terms, with more than a half of all 
suggested candidates being found among those that 
appeared exclusively in coordinations. However, 
these patterns also generated a number of false 
coordination expressions, and consequently a 
number of false term candidates. 
The integration of term variants was also useful 
for re-ranking of true positive term candidates: the 
combined rank was typically higher than the 
separate ranks of term variants. Furthermore, some 
terms, not suggested by the baseline method at all, 
were ranked highly when variants were conflated 
(for example, the term T-lymphocyte was 
recognised only as a coordinated term candidate, 
while replication of HIV-1 was extracted only by 
considering prepositional term candidates). In 
order to estimate the overall influence on recall of 
ATR, we used all terms from the respective 
synterms (see Table 4 for the detailed results). In 
general, the incorporation of inflectional variants 
increased recall by ¼, while acronyms improved 
recall by almost ⅔  when only the most frequent 
terms were considered. It is interesting that 
acronym acquisition can further improve recall by 
extracting variants that have more complex internal 
structures (such as EFs containing prepositions 
(REA = repressor of estrogen activity) and/or 
coordinations (SMRT = silencing mediator of 
retinoic and thyroid receptor)). Prepositional and 
coordination candidate terms had some influence 
on recall, in particular as they increased the 
likelihood of some candidates to be suggested as 
terms. Low recall of term coordinations may be 
increased by adding more patterns (which would 
probably negatively affect precision).  
Summarising, experiments performed on the 
GENIA corpus have shown that the incorporation 
of term variations into the ATR process resulted in 
significantly better precision and recall. In general, 
acronyms and inflectional unification are the most 
important variation types (at least in the domain of 
biomedicine). Individually, they increased 
precision by 20–70% for the top ranked synterm 
intervals, while recall is generally improved, in 
some cases up to 25%. Other term variations had 
only marginal influence on the performance, 
mainly because they were infrequent in the test 
corpus (compared to the total number of term 
occurrences, and not only with regard to specific 
individual candidates, but also in general). For 
these variations, larger-scale corpora may show 
their stronger influence.  
0
1
2
50
100 150 250 500
1000 1500 3000 5000
10000
al
l
prepositions inflectional acronyms
Figure 2a: Comparison of interval ATR precision 
of the baseline method (=1) to ATR precisions with 
integrated recognition of individual term variants 
(terms with frequency > 5) 
0
1
2
5
0
1
00
1
50
2
50
5
00
1
000
1
500
3
000
5
000
1
0000
al
l
prepositions inflectional acronyms
Figure 2b: Comparison of interval ATR precision 
of the baseline method (=1) to ATR precisions with 
integrated recognition of individual term variants 
(terms with frequency > 0) 
0
1
2
50
100 150 250 500
1000 150
0
300
0
50
00
10
000
a
ll
inflectional infl & acro all
Figure 2c: Comparison of interval ATR precision 
of the baseline method (=1) to ATR precisions with 
integrated recognition of combined term variants 
(terms with frequency > 0) 
 
term sets prep. coord. infl. acro. 
freq. ≥ 5 +5.30% +12.42% +17.52% +60.49%
freq. > 0 +2.36% +2.53% +25.25% +8.52% 
Table 4: Improvement in recall when variations 
are considered as an integral part of ATR 
 
5 Conclusion 
In this paper we discussed possibilities for the 
extraction and conflation of different types of 
variation of term candidates. We demonstrated that 
the incorporation of treatment of term variation 
enhanced the performance of an ATR system, and 
that tackling term variation phenomena was an 
essential step for ATR. In our case, precision was 
boosted by considering joint frequencies of 
occurrence and termhoods for all candidate terms 
from candidate synterms, while recall benefited 
from the introduction of new candidates through 
consideration of different variation types. Although 
we experimented with a biomedical corpus, our 
techniques are general and can be applied to other 
domains.  
Variations affecting single term candidate 
constituents are the most frequent phenomena, and 
also straightforward for implementation as part of 
an ATR process. The conflation of such term 
candidate variants can be further tuned for a 
specific domain by using lists of combining forms 
and affixes. The incorporation of acronyms had a 
significant high positive effect, in particular on 
more frequent terms (since acronyms are 
introduced for terms that are used more 
frequently). 
However, more complex structural phenomena 
had a moderate positive influence on recall, but, in 
general, the negative effect on precision. The main 
reason for such performances is structural and 
terminological ambiguity of these expressions, in 
addition to their low frequency of occurrence 
(compared to the total number of term 
occurrences). For handling such complex variants, 
a knowledge-intensive and domain-specific 
approach is needed, as coordinated term candidates 
or candidates with prepositions need to be 
additionally semantically analysed in order to 
suggest more reliable term candidates, and to 
introduce fewer false candidates.  
Apart  from being useful for boosting precision 
and recall, the integration of term variation into 
ATR is particularly important for smaller corpora 
(where linking related occurrences is vital for 
successful terminology management) as well as for 
many text-mining tasks (such as IR, IE, term or 
document clustering and classification, etc.). 
Finally, as future work, we plan to investigate 
more knowledge intensive, domain-specific 
treatment of prepositional and coordinated terms, 
as well as pronominal term references. 
6 Acknowledgements 
This research has been partially supported by the 
JISC-funded National Centre for Text Mining 
(NaCTeM), Manchester, UK. 

References  

S. Ananiadou, S. Albert and D. Schuhmann. 2000. 
Evaluation of Automatic Term Recognition of 
Nuclear Receptors from Medline. Genome 
Informatics Series, vol. 11. 

K.W. Church. 1995. One Term or Two? Proc. of 
SIGIR-95, pp. 310-318. 

B. Daille, B. Habert and C. Jacquemin. 1996. 
Empirical Observation of Term Variation and 
Principles for Their Description. Terminology 
3(2), pp. 197–258. 

K. Frantzi, S. Ananiadou and H. Mima. 2000. 
Automatic Recognition of Multi-Word Terms: 
the C/NC value method. International Journal of 
Digital Libraries, vol. 3:2, pp. 115–130. 

C. Jacquemin. 1999. Syntagmatic and paradigmatic 
representations of term variation. Proc. of 37th 
Annual Meeting of ACL, pp. 341–348. 

C. Jacquemin. 2001. Spotting and Discovering 
Terms through NLP. MIT Press, Cambridge MA. 

C. Jacquemin and E. Tzoukermann. 1999. NLP for 
Term Variant Extraction: A Synergy of 
Morphology, Lexicon and Syntax, in T. 
Strzalkowski (ed.), Natural Language 
Information Retrieval, Kluwer, pp. 25-74 

M. Krauthammer, A. Rzhetsky, P. Morozov, and 
C. Friedman. 2001. Using BLAST for 
identifying gene and protein names in journal 
articles. Gene, 259(1–2): pp. 245–52. 

GENIA. 2004. GENIA resources. Available at 
http://www.tsujii.is.u-tokyo.ac.jp/~Genia/ 

G. Nenadic, I. Spasic and S. Ananiadou. 2002. 
Automatic Acronym Acquisition and Term 
Variation Management within Domain-Specific 
Texts. Proc. of LREC 2002, pp. 2155–2162. 

G. Nenadic, I. Spasic and S. Ananiadou. 2004. 
Mining Biomedical Abstracts: What’s in a 
Term? Proc. of IJC-NLP, pp. 247-254.  

NLM. 2004. National Library of Medicine, Unified 
Medical Language System. 

Y. Tsuruoka and J. Tsujii. 2003. Probabilistic 
Term Variant Generator for Biomedical Terms. 
Proc. of 26th Annual ACM SIGIR Conference. 
