A Descriptive Framework for Translating Speaker's Meaning 
- Towards a Dialogue Translation System between Japanese and English - 
Masako KUME Gayle K. SATO 
ATR Interpreting Telephony Research Labs 
Sanpeidani, Inuidani, Seika-chd, Sdraku-gun, K yoto 619-02 JAPAN 
Kei YOSHIMOTO 
NTT Basic Research Labs 
Midori-chd 3-9-11, Musashino-shi, Tokyo 180, JAPAN 
Abstract 
A framework for translating speaker's 
meaning or intention is proposed based on two 
notions, Illocutionary Force Types (IFTs) for 
analysis and Decision Parameters (DPs) for 
generation. IFTs are a certain kind of 
classification of utterances concerning speaker's 
meaning. DPs present background information 
of language use in order to derive an appropriate 
expression from speaker's meaning. In Japanese, 
IFTs can be derived automatically through 
syntactical constraints. To generate appropriate 
expressions, language-specific communication 
strategies related to DP values should be given a 
priori. The whole process is performed in a 
unification-based framework. 
1. Introduction 
In devising a machine translation system of 
telephone dialogues, one of the problems is how to 
adequately translate tile underlying meaning of 
the source utterance, or the speaker's intention, 
into the target language. Such a concern is rarely 
observed in conventional machine translation 
research, which has focused on strictly 
grammatical translation divorced from 
consideration of the speaker's situation and 
intentions (Tsujii and Nagao 1988). However, in 
dialogue, smoothness of communication depends 
on perceiving the speaker's intention. Especially 
when dealing with different language family 
pairs such as Japanese and English, it is 
necessary to have a methodology of treating 
language-specific communication strategies in a 
universal framework. 
Although the input of our machine translation 
system is spoken dialogue, here we leave aside 
the issues of speech processing and limit our 
discussion to linguistic processing. Extra- 
grammatical sentence patterns such as intra- 
sentential correction, stammering, and inversion 
are not treated either. Our framework for 
translating speaker's intention is based on two 
notions, Illoeutionary Force Types (IFTs), i.e. a 
classification of the speaker's intentions, and 
Decision Parameters (DPs), i.e. features 
representing different factors relevant to speech- 
act-related expressions. Though plan-based 
approaches to speech acts such as Allen and 
Perrault (1980) are ideal, too little is known in 
this field to apply it to actual natural language 
processing. Therefore, we adopt here a moderate, 
intrascntential, syntactic method that can serve 
as further input to plan-based approaches. 
In section 2 of this paper we discuss the 
relation between intention and speech-act 
indirectness, and call intention thus described 
"speaker's meaning." In section 3 we define IFTs. 
In section 4 we fully utilize syntactic constraints 
in Japanese in order to extract II~rs from input 
utterances. In section 5 we present DPs as 
strategies for expressing IFTs in the target 
language. Finally, we make conclusions on this 
framework. 
2. Speaker's meaning in an utterance 
2.1. What Is speaker's meaning? 
When the speaker utters a sentence, the 
hearer receives communicative signs in addition 
to propositional content. According to speech act 
theory, these signs are classified as illocutionary 
forces governed by certain felicity conditions 
(Searle 1969). Speech act theory is one of the 
main themes of pragmatics, but it remains too 
conceptual to be of practical assistance to natural 
language processing. However, illocutionary 
forces can be useful to machine translation if 
propositional content is distinguished from 
structure in the analysis of intention. 
- 264- 
We begin by noting that intentions and 
surface expressions have multiple 
correspondences. As the following example 
shows, a single surface expression can convey 
several intentions: 
(2-1) gakusei waribiki wa nai no desy6 ks? 
student discount TOP exist-NOT EXPL-POL QUEST 
Isn't there a student discount? ll! 
REQUESTING 
COMPLAINING 
ADVISING 
CONFIRMING 
...etc. 
Conversely, the same intention can be conveyed 
through various surface expressions, as in the 
following variations of (2-1): 
REQUESTING 
Ill 
(2-2) gakusei waribiki o site kudasai. 
student discount OBJ make do-GIVFAV-POL-IMP 
Please make me a student discount. 
(2-3) gakusei waribiki o site itadaki tai 
student discount OBJ make do-RECFAV-PO|, want 
nodesu ga. 
EXI'I,-I'OL MODEl{ 
1 wonder ifyou could make me a student discount. 
(2-4) watasi wa gakusei na no desu ga. 
! TOP student COPL EXPL-POL MODER 
I am a student, you know. 
N.B. Concerning a 'discount' request, (2-2) seems a bit 
strong for a real situation although there is no specific 
contexttml condition to decide definitely if it is or not. (2-1) 
(2-3) and (2-4) are seen in our data. 
These examples clearly show that intention is 
context-dependent, and that to understand the 
speaker's meaning correctly, an inference 
mechanism is necessary. 
Various surface expression patterns give clues 
for ascertaining illocutionary forces (Wierzbicka 
1986). 
(2-5) t~rokuydsi o o-okuri negae masu ks? 
registration form OBJ send-POL desire POL QUEST 
Can you please send me a registration form7 
(2-6) Could you kindly send them all together? 
Hegau in (2-5), a verb for request, and ks, the 
sentence-final particle of questions, indicate 
request. Kindly in (2-6) signals a request in 
English. In other words, even without knowledge 
of the context of an utterance, knowledge of 
communicstive strategies of language and their 
expression patterns allow the derivation of 
intentions from utterances. 
In the above examples, we can see there are 
various ways of expressing requests. This 
indirectness derives from social patterns in 
requesting things common to all cultures to some 
degree. On the other hand, however, it depends 
on each specific society. In this paper we accept 
indirectness as an unavoidable and basic feature 
of spoken utterances, and deal with indirect 
patterns such in (2-1) and (2-3) that will be called 
speech-act indirectness. Indirect expressions such 
as (2-4), which are called propositional 
indirectness, are not treated for the reason given 
in the next subsection. We use the term speaker's 
meaning to refer to intention expressed by 
speech-act indirectness. Using this notion, we try 
to capture syntactically the major portion of 
speech-act-related expressions in spoken 
Japanese. 
2.2. Translation of speaker's meaning 
We assume that for machine translation it is 
sufficient to understand utterances on the level of 
speech-act indirectness, without referring to 
propositional indirectness. On the one hand, 
when there is a large degree of indirectness such 
as the omission of propositional content in (2-4) 
where the topic "discount fee for students" is not 
actually mentioned, we must be content with a 
direct translation of what has been stated. This is 
because a sentence-based translation cannot 
compensate for the missing content. In addition, 
since the hearer will no doubt be able to infer 
something about the omitted content anyway, the 
speaker is best served by a direct translation 
closest to the original. On the other hand, when 
the propositional content is explicitly phrased but 
requires indirectness to make an appropriate 
translation into the target language, a system 
that concentrates on speech-act indirectness will 
again be tile most useful, because socio-linguistic 
differences will be expressed typically in speech- 
act indirectness as in (2-1) and (2-3). 
Consequently, we develop a framework aimed at 
extracting speaker's meaning in terms of speech- 
act indirectness. 
3. I FTs 
3.1.Classiflcatlon of IFTs 
An experiment has been carried out on 
collected data of spoken-style inter-terminal 
dialogues to extract illocutionary acts. The 
subject of the conversations was limited to 
- 265 - 
application for an international conference, and 
the content was mainly on inquiry, request, and 
confirmation about the conference between a 
secretary and an applicant. 
We classify surface IFTs into six types (Table 
1). This is the immediate result of the analysis 
made intrasententially by means of Head-Driven 
Phrase Structure Grammar (HPSG)/Japanese 
Phrase Structure Grammar (JPSG). The six 
types are differentiated from each other only by 
means of the uppermost predicate value that is 
the result of the surface-based analysis. For 
example, an indirect request with an inter- 
rogative sentence pattern such as 
(2-5) t6rokuySsi o o-okuri negae masu ha? 
Could you please send me a registration form? 
is classified simply as an INTERROGATIVE 
type, though it is OPTATIVE at the deep IFT 
level. Also, a sentence with an active, present- 
tense verb such as 
(3-1) tdrohuyOsi o o-ohuri si masu 
registration form OBJ send-POL do-POL 
I will send you a registration form. 
is analyzed as INFORMATIVE, though it is 
PROMISE at the deep level. 
Table 1. SurfacelFTs 
surface surface IFT instances 
predicate value 
F,X PRESS! VI~ arlgat6 (thanks) arlgal6- sumimasen (sorry) THANKS, etc. 
mosimosi (hello) mosimosi- I'liN\['lC 
say, nora (goodbye) ltELLO, etc. 
negau (wish) x-REQU EST OPTATIVE kudasai (please) 
QUESTIONIF I NTI~RI~,OGATI VE 
ha, ne QUESTIONREF 
tai (want) SU BJ ECTIVE hosii (want...to) x-WISH 
INFORMATIVR various S-INFORM 
3.2.Unification-based analysis 
Figure 1 diagrams an overview of the 
procedure for translating speaker's meaning. In 
contrast to a conventional machine translation 
procedure, speaker's meaning can be analyzed 
and generated, without passing through transfer, 
by means of IFTs and DPs. Here, we do not 
pursue machine translation problems concerning 
propositional content. The processing of 
speaker's meaning consists of two stages, 
unification-based syntactico-semantic analysis 
and plan inference. We will now give a more 
precise description of these two stages. 
INPUT 1 
analysis l-- 
I I t. ......... .J 
extraction 
of IFTs 
r ........ "! 
I ! .j transfer ,I- 
t ........ .I 
> 
OUTPUT 
l 
r ......... l 
-~igenerationi 
t. ......... J 
forms based 
on DPs 
Figure 1. Speaker's meaning translation procedure 
As a grammar for surface-level analysis, we 
have adopted HPSG (Pollard and Sag 1987) and 
JSPG (Gunji 1987), that is a modification of the 
former for dealing with Japanese. On the basis of 
a unification parser developed at ATR (Kogure et 
al. 1988), the grammar has been written and 
proven capable of analyzing all fundamental 
sentence patterns in spoken-style Japanese 
conversation (Yoshimoto, Kogure and Iida 1989). 
This grammar analyzes sentence (3-2) as (3-3) 
by means of syntactic rules and lexical 
descriptions, of which only those for the 
subsidiary verb morau are given as (3-4). 
(3-2) t6rokuy~si o Okutte morse rnasu ka? 
registration form OBJ send RECFAV-POSS POL QUEST 
(lit.) Could I have the favor of your sending me a 
registration form? 
(3-3) 
\[\[SEM \[\[RELN QUESTIONIF\] 
\[AGEN ?SP\] 
\[RECP ?HR\] 
\[OBOE \[\[RELN RARERU-POSSIBLE\] 
\[OBOE \[ \[MORAU- RECEIVE- FAVOR\[ 
\[AGEN zxI\] 
\[ORIG ?X2\] 
\[OBOE \[\[RELN OKURU-|\] 
\[AGEN ?X2\] 
\[RECP ?Xl\] 
\[oBoe TOROKUY~)SI ' \]\]\]\]\]\] \]\]\] 
\[SLASH {\[\[HEAD \[\[POS P\]\[FORN GA\]\[GRF SUBJ\]\]\] 
\[SUBCAT {}\] 
\[SeN ~xl\]\] 
\[\[HEAD \[\[POS P\]\[FORM NI\]\[GRF OBJ2\]\]\] 
\[SUBCAT \[}\] 
\[SEN ?X2\]\])\] 
\[PRAG (\[\[SPEAKER ?SP\] 
\[HEARER ?HR\] 
\[RESTR$ {\[\[RELN EMPATHY-DEGREE\[ 
\[STAM ZSP\] 
\[MORE ?Xl\] 
\[LESS TX2\]\] 
\[\[RELN POLITE\] 
\[AGEN ?SP\] 
\[OBOE ?HR\]\]}\]\]}\]\] 
- 266 - 
(3-4) 
(DEFLEX more V () 
\[\[.EAD \[\[POS V\] 
\[\[TYPE CONS-UV\] 
\[croRM STEM\] 
\[MODL \[\[DONT BEND\]\]\]\]\] 
\[SUB\[AT {\[\[HEAD \[\[POS P\[ 
\[FORM GA\] 
\[GRF SUBJ\]\]\] 
\[SUB\[AT ()\] 
\[SEM ?XJ\]\] 
\[\[HEAD \[\[POS P\[ 
\[FORM NIl 
\[GRF OBJ2\]\]\] 
\[SUB\[AT {}\] 
\[SEM ?X2\]\] 
\[\[HEAD \[\[POS V\[ 
\[\[FORM TE\] 
\[MODL \[IDEA\[ PASS\[\[ASP\[ PROG\] 
\[PONT BENO\]\] IOPTT-\]\]\] 
\[SUB\[AT {\[\[HEAD \[\[POS P\] 
\[FORM GA\] 
\[GRF SUBO\]\]\] 
\[SUBCAT {\]\] 
\[SEM ?X2\]\]}\] 
\[SEM ?SEMI\[)\[ 
\[SEM \[\[RELN MORAU-RECEIVE-FAVOR\] 
\[AGEN ?Xl\] 
\[RECP ?X2\] 
\[OBOE ?SEMI\[\[ 
\[PRAG \[\[SPEAKER ?SPEAKER\] 
\[HEARER ?HEARER\] 
\[RESTRS (\[\[RELN EMPATHY-DEGREE\[ 
\[STAN ?SPEAKER\] 
\[MORE ?Xl\] 
\[LESS ?XZ\]\]}\]\]\]\]) 
'?' is a prefix for a tag name representing a 
token identity of feature structures. In (3-4), the 
third member of the SUBCAT value specifies the 
conjugational form and modality type of the 
complement verb. The feature MODL imposes 
conditions on the modality type that plays a key 
role in Japanese syntax by dominating mutual 
predicate component subcategorization and 
subordination. In order to handle the unordered- 
hess of Japanese case phrases, the SUB\[AT 
value is a set, following JPSG, instead of an 
ordered list in the HPSG for English. The set is 
expanded by a rule reader into its corresponding 
possible ordered list descriptions. Since Japanese 
case phrases are always postposed by a case- 
indicator, they are assigned to the part-of-speech 
category P. The PRAG feature stipulates here 
that the speaker empathizes more with the 
subject (?X1 in (3-4)) than with the indirect object 
(?X2). 
This pragmatic information is further utilized 
with a discourse model to identify omitted 
subjects and objects, because they are mostly 
omitted in honorific or empathy-related 
sentences. 
4. Identification of IFTs 
The surface analysis result such as (3-3) 
serves as an input to plan schemata called IFT- 
Schemata that identify deep IFTs (or merely 
IFTs) syntactically by means of predicate- 
internal collocation, adjunction, tense, and modal 
information. An IFT-Schema consists of a goal 
whose value is a partial description of a deep IFT, 
and a decomposition whose value is a disjunction 
of partial descriptions of surface IFTs, 
preconditions, and effects as in (4-1), (4-2) and (4- 
3). A surface IFT is searched for which unifies 
with one of the descriptions in the decompostion. 
The goal in the same schema is the resulting deep 
IFT. Adoption of the unification method enables 
hi-directional flow of information between the 
deep speech act type and the decomposition. This 
leads to an easier disambiguation and 
supplementation of surface analysis results by 
linguistically specifying IFTs (Kogure et el. 
1988). 
The difference between surface analyses and 
deep IFTs is absorbed by a "thesaurus", as in (4- 
4), that relates the two. This specifies that 
MORAU-RECEIVE-FAVOR is a subtype of 
RECEIVE-FAVOR. (4-5) is the result of the IFT 
inference. 
(4-1) 
(DEF-IFT-SCHEMA ?REQ\[\[RELN REQUEST\] 
\[AGEN ?sp\] 
\[~ECP ?HR\] 
\[OBOE ?OBJCCAGEN ?XB\]\]\] 
\[MANN INDIRECTLY\] 
\[ATTD INTERROGATIVELY\]\] 
: DECOMPOSI T ION 
(;MORAE MASE N KA, \[TADAKE MASE N KA 
\[\[RELN QUESTION\[ F\[ 
\[AGEN ?HR\] 
\[RECP ?sp\] 
\[OBOE \[\[RELN NEGATION\[ 
\[TENSE PRESENT\] 
\[OBOE \[\[RELN POSSIBLE\] 
\[AGEN ?SP\] 
lOBaR \[\[RELN RECEZVE-FAVOR\] 
\[AGEN ?SP\] 
\[SOUR THe\[ 
\[OBOE ?OBO\]\]\]\]\]\]\]\] 
,..) 
;NEGAE MASU KA 
\[\[RELN QUESTION\[F\[ 
\[AGEN ?HR\] 
\[RECP ?SP\] 
\[OBJE \[\[RELN POSSIBLE\] 
\[TENSE PRESENT\] 
\[AGEN ?SP\] 
\[OBOE \[\[RELN REQUEST\] 
\[AGEN ?SP\] 
\[RECP ?HR\] 
\[OBOE ?OBJ\]\]\]\]\]\] 
- 267- 
(4-2) 
(DEF-IFT-SCHEMA ?REQ\[GRELN REQUEST\] 
\[AGEN ?SP\] 
\[RECP ?HR\] 
\[OBOE ?OBJ\[\[AGEN ?He\]\]\] 
\[MANN INDIRECTLY\] 
\[ATTD DECLARATIVELY\]\] 
:DECOMPOSITIONS 
(;MORAI TAI NO DESU GA, 
;ITADAKI TAI NO DESU GA 
\[\[RELN S-INFORM\] 
\[OBOE \[GREEN MODERATE\] 
\[OBOE \[\[RELN DESIRE\] 
\[TENSE PRESENT\] 
\[EXPN ?SP\] 
\[OBOE \[\[RELN RECEIVE-FAVOR\] 
\[AGEN ?SP\] 
\[SOUR ?HR\] 
\[OBOE ?OBJ\]\]\]\]\]\]\]\] 
• ..) ) 
(4-3) 
(DEF-IFT-SCHEMA ?REQGGRELN REQUEST\] 
\[AGEN ?SP\] 
\[RECP ?HR\] 
\[OBOE ?OBO\[GAGEN ?HR\]\]\] 
\[MANN DIRECTLY\] 
\[ATTO DECLARATIVELY\]\] 
:DECOMPOSITIONS 
(;KURE, KUDASAI 
\[\[flELN REQUEST\] 
\[AGEN ?SP\] 
\[SOUR ~He\] 
\[OBJE ?OBOE\] 
• ..) ) 
(4-4) 
(RELATION-IS-A MORAU-RECEIVE-FAVOR RECEIVE-FAVOR) 
(REEATION-IS-A ITADAKU-RECEIVE-FAVOR RECEIVE-FAVOR) 
(RELAIION-IS-A KA-QUESTIONIF INFORMIF) 
(EELATION-IS-A NARERU-POSSIBLE POSSIBLE) 
(RELATION-IS-A DEKIRU-POSSIBLE POSSIBLE) 
By this mechanism, the IFT of sentence (3-2) 
is inferred as (4-5). 
(4-5) 
\[GRELN REQUEST\] 
GAGEN ?sp\] 
GRECP ?HR\] 
\[OBOE \[GREEN OKURU-I\] 
GAGEN ?HR\] 
\[flECP ?SP\] 
\[OBOE TOROKUYOSI'\] 
\[MANN INDIRECTLY\] 
\[AITD INTERROGATIVELY\]\] 
In identifying deep IFTs, syntactic constraints 
in Japanese are fully utulized. 
On the one hand, IFTs SUBJECTIVE and 
OPTATIVE are universally limited to 
expressions with first person singular subject and 
present tense and without modal information, 
and Japanese surface predicates reflect these 
restrictions very well. Also, OPTATIVE is 
limited to second person recipient. For example, 
(4-6) ¢SBJ kaigi ni mdsikomi tai. 
conference OBJ2 reserve want 
I would like to register for the conference. 
(4-7) ~SBJ kaigi ni mdsikomi tai sd do. 
conferenceOBJ2 reserve want l-hear 
I hear (someone) wants to register for the conference. 
While sentence (4-6) with the present, non-modal 
auxiliary tai (want to) belongs to the 
SUBJECTIVE type, (4-7) with the evidential 
modality belongs to the ASSER'ITVE type. This 
fact is utilized, by means of two lexical 
descriptions of tai and IFT-Schemata restricting 
the decomposition members' person, tense, and 
modal information, to identify the omitted subject 
of(4-6) as the first person, and that of(4-7) as the 
third person. 
On the other hand, adverbials that exclusively 
modify deep IFTs are also utilized in 
disambiguating IFTs, For example, a sentence 
with O-Regal simasu (request, implore) is 
ambiguous among OPTATIVE, ASSERTIVE, 
and PROMISE. If it is modified by dEzo (please), 
however, the sentence is always an OPI'ATIVE 
type. 
Deep IFTs with their corresponding syntactic 
constraints are diagramed by Table 2. Instances 
in the Table indicate each of the corresponding 
deep IFTs, but the opposite is not necessarily 
true. For example, a deep IFT OPTATIVE can be 
indicated by complex predicates that belong to 
the surface category INTERROGATIVE or 
ASSERTIVE. Table 3 illustrates the relation 
between the deep IFT OPTATIVE and its 
corresponding surface IFT with instances. 
Table 2. Deep IFTs and Constraints (Part) 
surface IFT syntactic constraints adjuncts 
EXPRESSIVE d~mo 
1st pers., sing. sbj. dEzo, dEha, 
OPTAT! VE 2nd person obj2 sumimaseen 
present, non-modal (go) 
ittai, INTERROGATIVE 
somosomo 
SUBJECTIVE zehi IsL pers., sing. sb.i. ; present, non-modal 
- 268 - 
Table 3. Surface Expressions for Deep OPTATIVE 
surface IFT 
OPTATIVE 
INTERROGATIVF~ 
SUBJECTIVE 
ASSERTIVE 
instances with literal 
translation 
...te hosii n desu ga 
(I would like you to...) 
o-negai si masu 
(I request you to...) 
...re hure masu ha? 
(will you do me the favor of...) 
...re kure masen ks? 
(won't you do me the favor of...?) 
te morae masu ha? 
(can I receive the favor of...?) 
...tain desu ga 
(I would like to...) 
...re morai tain desu ga 
(I 'd like to receive the favor of...) 
...re morai masu 
(I will receive the favor of...) 
...to arigatai n desu ga 
(I would be happy if you...) 
By so specifying the IFT, information absent 
in surface utterances such as zero anaphora are 
compensated for and in some cases multiple 
analyses are disambiguated. (3-3), the surface 
analysis of (3-2), is analyzed as (4-5). This 
enables an adequate English translation (4-8) 
instead of an inappropriate literal translation (4- 
9). Note that at the same time the subject and 
indirect object missing in the surface sentence are 
compensated for by the IFT specification of the 
agent and recipient. 
(4-8) Could you send me a registration form? 
(4-9) *Can I receive a favor of your sending me a 
registration form? 
5. Dl's 
5.1. Necessity of DPs 
We can summarize the difference between 
Japanese and English communication behavior 
as follows: 
Japanese interpersonal relation is the most 
essential factor 
English interpersonal relation is 
essential, but how to convey or 
read intentions is more 
important 
For example, (5-1) is an utterance from a boss to a 
secretary to request him to work overtime. This 
Japanese utterance is not an order because it is 
expressed in a polite way using the negative 
interrogative. This kind of request is not unusual 
in Japanese because of the priority given to social 
standing. Because Japanese think a request 
phrased like this is normal, the English 
translation shown in (5-1) using can and sorry 
seems appropriate to them, too. But actually an 
appropriate translation requires a more polite 
expression that addresses the secretary's 
inconvenience, as in (5-1)'. Thus, to get an 
appropriate translation of (5-1), we must 
reconsider from the viewpoint of the target 
language interpersonal relations between the 
speaker and the hearer and the inconvenience of 
requested action for the hearer. 
(5-1) sumanaiga, zangyd site syorui o 
sorry work overtime documentsOBJ 
taipu site kure nai ha na? 
type do-GIVFEV NEG QUEST 
Sorry, but can you stay late to type these documents? 
(5-1)' Do you think you could possibly stay late 
to type these documents? 
To resolve these communicative differences 
between Japanese and English, we assume four 
kinds of parameterlzed factors, which we call 
Decision Parameters (DPs). These are: 
interpersonal relation, cost-benefit relation, 
definiteness of propositional content, and 
topicality of propositional content. Interpersonal 
relation indicates the situational relationship 
between utterance participants as constituted by 
age, social status, familiarity, gender, and the 
other factors governing use of Japanese 
honorifics. Cost-benefit relation indicates 
whether the action intended by the speaker's 
utterance is convenient to the speaker or to the 
hearer. Definiteness of propositional content 
means whether propositional content is routine 
or easily performed work, or whether it requires 
additional or unusual work. Topicality of 
propositional content is related to the position of 
an utterance in discourse, which means whether 
or not the speaker's intention is already implied. 
Table 4 shows these four parameters and their 
values. In particular, DP4 or topicality presents 
discourse information which affects the 
politeness level of surface expressions. In the 
present experimental situation, extraction of 
speaker's meaning is limited to isolated 
utterances separate from discourse structure, but 
- 269 - 
to get appropriate expressions in generation, we 
need DP4 in connection with a discourse model. 
Table 4. DPs and values 
DPs 
1 interpersonal 
relation 
Values 
authority in HR / 
a. inSP / EQual 
2 cost-benefit convenient for HR / 
relation c. forSP / NoMarK 
3 definiteness of ROUtine I UNuSual 
propositional content 
4 topicality of + I 
propositional content 
5.2. Selection of surface IFT by referring to 
I)P values 
In the plan inference method of generation, we 
use DPs in order to get appropriate English 
surface IFTs to convey IFTs in English. Since we 
are limiting the input to a task-oriented domain 
like conferences, we can re-state input in terms 
of propositional content. This propositional 
content is then measured in terms of the three DP 
values as a default (Table 5). 
Table 5. Default values of DPs 
Propositional Content DP1 DP2 DP3 
\[A\] Request 
(from a client to a secretary)* 
(1) send a registration form HR SP ROU 
(2) inform about the conference HR SP ROU 
(3) assist a hotel accomodation HR SP ROU 
(4) provide an interpreter HR SP UNS 
(5) give a student discount HR SP UNS 
(6) reimburse a fee HR SP UNS 
(7) come for to the station HR SP U NS 
\[S\] Request 
(from a secretariy to a client) 
(8) send back the registration form HR SP ROU 
(9) tell one's name and address HR SP ROU 
(10) make a registration procedure HR SP ROU 
(11) pay by bank transfer HR SP UNS 
(12) take part in the party HR SP UNS 
(13) be informed about persons HR SP UNS 
who wish to participate 
*In bt, siness telephone conversations in English, the 
hearer is always considered to be in a higher position, 
even in the case of a boss to a secretary. So the value of 
DP1 for \[A\] is always IlR. 
We suppose that differences between Japanese 
and English consist in the different amount of 
DPs we should refer to when extracting surface 
IFTs. Japanese surface IFTs will be concerned 
with DP1 and DP2 since Japanese expressions do 
not stress speaker's intention, whereas English 
surface IFTs will range over all four DPs and 
produce a larger range of appropriate translation 
choices. 
For example, (1) and (7) ofTable 5 which differ 
in definiteness of propositional content (i.e. 
routine or unusual), can be generated in the same 
way in Japanese, which involves only DP1 and 
DP2. That is, 
(5-2) t6rokuydsi o okut-te moral tai 
registration form OBJ send do-RBCFAV want 
no desu ga. ---(1) 
EXPL-POL MODER 
(5-3) eki made mukaeni hi-re moral tai 
station LOC come for do-RECFAV want 
no desu ga. ---(7) 
EXPL-POL MODER 
In English, however, these propositional contents 
will be generated in different expressions. In case 
(7), to convey the unusual but really necessary 
'picking up' request, an adequate expression 
requires more politeness. 
(5-2)' Could you sehd me a registration form 
please? ---(1) 
(5-3)' Ca) I was wondering ifl could have someone 
pick me up at the station. ---(7) 
(b) Would it be possible for someone to pick 
me up at the station, please? ---(7) 
With reference to discourse information, DP4, 
the appropiate English surface IFT will be graded 
up or down depending on its position in the 
discourse. The mapping from Japanese surface 
IFT to English surface IFT is schematized as in 
Table 6. We can categorize English request 
expressions into two kinds. One is direct 
expressions with please, which we call PLEASE, 
and others are expressions containing several 
levels of politeness such as could you...?, is it 
possible to...?, I am wondering, etc., which we call 
PLEASE-PLUS. Japanese surface IFTs are 
separated into two types, INTERROGATIVE and 
others, i.e. declarative requests using 
OPTATIVE, SUBJECTIVE or ASSERTIVE type. 
When a Japanese surface IFT is 
INTERROGATIVE as in (5-4) and (5-5), and if 
the IFT is already implied in preceding 
utterances, the English surface IFT can be 
- 270- 
expressed simply with PLEASE type as in (5-4)' 
and (5-5)', otherwise it should be expressed in 
PLEASE-PLUS type such as several kinds of 
English speech-act indirectness as in (5-4)" and 
(5-5)". On the other hand, when the Japanese 
surface IFT is others such as OPTATIVE or 
SUBJECTIVE as in (5-2) and (5-3), and if IFT is 
already implied in preceding utterances, the 
English surface IFT should be expressed in 
PLEASE-PLUS as in (5-2)" and (5-3)". 
Table 6. Mapping relation concerning DP4 
J. surface IFT DP4 E. surface IFT 
+ PLEASE INTERROGATIVE 
Others -I- 
PLEASE-PLUS 
PLEASE-PLUS 
PLEASE 
(5-4) t~rokuy6si o okut-te morse masu ka?(1) 
registration form OBJ senddo-RECFAV POL QUEST 
(5-4)' . .... so please send me a registration form. 
(5-4)" Hello, is it possible to send me a registration 
form? 
(5-5) eki made mukae ni ki-te morse masu ha?(7) 
station LOC comet or do-RECFAV POL QUEST 
(5-5)' ..., then please pich me up at the station. 
(5-5)" I am calling you because I was wondering if 
you could possibly send someone to pick me 
up at the station. 
(5-2) t6rokuy6si o okut-te moral tai 
reglstrationform OBJ send do-RECFAV want 
no desu ga. ---(1) 
EXPL-POL MODER 
(5-2)" ...then, I would appreciate it if you could 
send me a registration form. 
(5-3) eki made mukaeni ki-te moral tai 
station LOC eomefor do-RECFAV want 
no desu go. ---(7) 
EXPL-POL MODER 
(5-3)" ...so, may I ask if you could possibly have 
someone pick me up at the station? 
Thus, the politeness levels of English surface 
IFTs in terms of speech-act indirectness are 
appropriately generated by clarifying the 
relation between English surface IFTs and DPs. 
6. Conclusion 
We proposed in this paper a descriptive 
framework for translating speaker's meaning in a 
dialogue translation system. This framework is 
based on two notions, Illocutionary Force types 
and Decision Parameters, and is aimed at 
extracting speaker's meaning in terms of speech- 
act indirectness since we believe that 
propositional and speech-act indirectness must 
both be processed separately. 
Acknowledgments 
The authors are grateful to Dr. Kurematsu, 
the president of ATR Interpreting Telephony 
Research Labs, Dr. Aizawa, the head of the 
Linguistic Processing Department, and all the 
members of the Linguistic Processing 
Department for their constant help and 
encouragement. 
References 
Allen, James and Raymond Perrault, 1980, "Analyzing 
Intention in Utterances." Artificial Intelligence 15, 143-78. 
Gunji, Takao, 1987, Japanese Phrase Structure Grammar. 
Reidel. 
Kogure, Kiyoshi et al., 1988, "A method of analysing 
Japanese speech act types", Proc. of 2nd Itl. Conf. on 
Theoretical and Methodological Issues in Machine 
Translation of NaturalLanguages. 
Maeda, Hiroyuki, et al. 1988, "Parsing Japanese honorifics 
in unlfication-based grammar." Proc. of the 26th Annual 
Meeting of the Association of Computational Lingulstics. 
Pollard, Carl and Ivan Sag, 1987, Information-Based 
8yntax and Semantics. vol. 1. CSLI Lecture Notes 13. 
Sanford, D. and J Roach, 1987, "Representing and using 
metacommunieation to control speakers' relationships in 
natural-language dialogue", Int. J. of Man-Machine 
,Studies, 28, 301-319. 
Scoria, J., 1969, Speech Acts. Cambridge University Press. 
Scoria, J., 1979, Expression and Meaning; Studies in the 
Theory of Speech Acts. Cambridge Univ. Press. 
Ts~ii, J. and M. Nagao, 1988, "Dialogue Translation vs. 
Text Translation -hlterpretation Based Approach-", Proc. of 
Coling 88. 
Yoshimoto, Kei, 1987, "Identification br Zero Pronouns in 
Japanese." The XIVth International Congress of Linguists. 
Aug. 10, Berlin. 
Yoshimoto, Kei, 1988, "Identifying Zero Pronouns in 
Japanese Dialogue." Proc. of Coling 88. 
¥oshimoto, Kei, Kiyoshl Kogure and tlitoshl lids, I989, 
"llead-Driven Phrase Structure Grammar for Japanese 
Dialogue Analysis." Unpublished manuscript, ATR. 
Wierzbicka, A., 1986, "A semantic metalanguage for the 
description and comparison of illocutlonary meaings", 
Journal of Pragmatics 10, 67-107. 
- 271 - 
