File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/98/p98-1090_metho.xml
Size: 23,003 bytes
Last Modified: 2025-10-06 14:14:54
<?xml version="1.0" standalone="yes"?> <Paper uid="P98-1090"> <Title>Long Distance Pronominalisation and Global Focus</Title> <Section position="4" start_page="550" end_page="550" type="metho"> <SectionTitle> 2 Theories of focus </SectionTitle> <Paragraph position="0"> Space unfortunately prevents a full discussion of Grosz's (1977), Sidner's (1979), and G&S's (1986) theories of focus and the attentional state in this abstract. The crucial aspects of these theories, for the purpose of the discussion below, are as follows.</Paragraph> <Paragraph position="1"> First of all, G&S propose a distinction between two components of the attentional state: the GLOBAL FOCUS, structured as a stack of focus spaces and accessed to interpret definite descriptions; and the LO-CAL FOCUS, consisting of the information preferentially used to interpret pronouns* In addition, they adopt CENTERING THEORY (Grosz et al., 1995) as a theory of the local focus.</Paragraph> <Paragraph position="2"> Secondly, although G&S's theory integrates ideas from both Grosz's and Sidner's original theories, and although both of these theories assumed a stack structure, the global focus in G&S's theory is structured as a stack of focus spaces, as in Grosz's original proposal, rather than as a stack of discourse foci, as in Sidner's original theory. The claim that different parts of the attentional state are accessed when resolving pronouns and definite descriptions is supported, broadly speaking, by psycholinguistic research (see, e.g., (Garrod, 1993)).</Paragraph> <Paragraph position="3"> The main claims of centering theory are also consistent with psycholinguistic results (Hudson, 1988; Gordon et al., 1993). To our knowledge, however, the choice of a stack of focus spaces over a stack of discourse foci has never been motivated; yet this decision plays a crucial role in our problem, as we will see.</Paragraph> <Paragraph position="4"> A point worth keeping in mind throughout the following discussion is that, although the concept * O&quot; of c8 (centerm~ theory s name for the current most salient entity) was originally introduced as 'roughly corresponding to Sidner's concept of discourse focus', in fact it is not clear that the two concepts are capturing the same intuitions (Poesio and Stevenson, 1998). Although it is often the case that the CB and the discourse focus coincide, this is not true in general.I For the purposes of this paper, however, we will assume that the two notions do coincide, and will use the neutral term MOST SALIENT ENTITY (MSE) to refer to the discourse focus / CB of a particular segment of text.</Paragraph> <Paragraph position="5"> ~This intuitive impression was confirmed by a recent study (Giouli* 1996), whose author tracked both the 'intuitive CB' and the 'intuitive discourse focus' of 8 Map Task conversations.</Paragraph> </Section> <Section position="5" start_page="550" end_page="550" type="metho"> <SectionTitle> 3 The Data </SectionTitle> <Paragraph position="0"> The Intelligent Labelling Explorer (ILEX) project is building a system that generates descriptions of objects displayed in a museum gallery. 2 In order to generate the most natural descriptions of the objects, dialogues with a museum curator were collected, describing objects in the National Museum of Scotland's 20th Century Jeweilery Gallery. We will refer to this corpus as the ILEX corpus. In the dialogues, the curator (LG) moves from case to case as directed by an observer (JO) and describes the jewels in each case, as in example (1).</Paragraph> <Paragraph position="1"> The work described here is part of two related projects: SOLE, the goal of which is to extend the ILEX system with the capability of generating prosodically adequate speech, and GNOME, which is concerned with the generation of nominal expressions. A second corpus of museum object descriptions was collected for use with SOLE; we will refer to this corpus as the SOLE COrpUS.</Paragraph> </Section> <Section position="6" start_page="550" end_page="552" type="metho"> <SectionTitle> 4 Analysis </SectionTitle> <Paragraph position="0"/> <Section position="1" start_page="550" end_page="551" type="sub_section"> <SectionTitle> 4.1 First Hypothesis </SectionTitle> <Paragraph position="0"> Because G&S's theory of the attentional state already hypothesises global focus structures in addition to the local attentional structures assumed in centering theory, the simplest explanation for our cases of long-distance pronominalisation is to hypothesise that readers exploit the global focus to resolve pronouns in such cases.</Paragraph> <Paragraph position="1"> Assuming that the global focus is involved in these cases, instead of complicating the local focus/centering theory, is consistent with the little available psychological evidence --e.g., with the resuits of Clark and Sengui (1979), who observed a slowdown in reading times for the sentence containing the pronoun when the antecedent is not in the same or the previous sentence, implying that long-distance pronominal anaphora are handled differently. null Furthermore, suggesting that these pronouns are resolved by accessing the global focus would not really amount to a revision of the basic assumptions of G&S's theory. Although no explicit proposal conceming the respective roles of local focus and global focus in pronoun resolution has ever been made in the literature on the G&S framework, cases of pronouns involving access to the global attentionai structure rather than to the local focus have ~'http: //www.cogsci .ed.ac.ukfalik/ilex/ systemintro, html already been discussed in this literature. So-called RETURN-POPS, which are pronouns that signal a return to a superordinate discourse segment, were discussed by Grosz (1977) and then in detail in (Fox, 1987). In (2), for example, sentence 5 resumes the segment interrupted by 2-4; the antecedent for the pronoun her is supposed to be found on the stack, although the details of this process have never re- null ally been discussed. 3 (2) 1. C: Ok Harry. I'm have a problem that uh my-with today's economy my daughter is working, 2. H: I missed your name.</Paragraph> <Paragraph position="2"> 3. C: Hank.</Paragraph> <Paragraph position="3"> 4. H: Go ahead Hank.</Paragraph> <Paragraph position="4"> 5. C: as well as he___zr husband A second case of pronouns that clearly seem to involve access to some global structure are so-called 'generic' pronouns, such as the, in (3): (3) John went back to the hotel. He looked for Mary in their room, but couldn't find her. They told him that she had left about an hour earlier. (We are not aware of any account of these uses of pronouns within the G&S framework.) As we will see in a moment, the long-distance pronouns observed in the ILEX dialogues are neither generic pronouns nor return-pops; nevertheless, we are going to show that these cases, as well, are resolved by accessing the global focus.</Paragraph> </Section> <Section position="2" start_page="551" end_page="551" type="sub_section"> <SectionTitle> 4.2 Long-distance pronouns need not be </SectionTitle> <Paragraph position="0"> return-pops Tile use of him in the last sentence of (1) could only be termed a RETURN-POP if it were to involve a return to the previous discourse segment which 'pops over' sentence 4 (And if you look at, for instance, the bangle at the bottom ... ) and 'closes off' the material introduced in that sentence. But this is clearly not the case, as shown by the fact that the final sentence contains a reference to both the jeweller and the bangle. Indeed, the bangle could also be referred to with a pronoun: And it took him something like 120 hours of work. The fact that pronouns and definite NPs in the last sentence can refer back to material in the 4th sentence indicates that this material must still be on the stack.</Paragraph> </Section> <Section position="3" start_page="551" end_page="552" type="sub_section"> <SectionTitle> 4.3 Discourse Structure in the Example Text </SectionTitle> <Paragraph position="0"> Before discussing how the global focus is used for resolving pronouns such as the long-distance pronoun in the last sentence of (1), we need to discuss the structure of these examples: i.e., is the part of (l) which has the jeweller as MSE (2nd sentence) still on the stack when the part that describes details of the jewel and contains the long-distance pronoun (3rd and 4th sentence) is processed? Answering this question is made more difficult by the fact that G&S's theory of the intentional structure is very abstract, and therefore does not help much in specific cases, especially when the genre is not task-oriented conversations. More specific indications concerning the structure of the relevant example, and more in general of the conversations in the ILEX corpus, are given by Rhetorical Structure Theory (RST) (Mann and Thompson, 1988), 4 although even with RST it is still possible to analyse any given text in many different ways. Nevertheless, we believe that the structure depicted in Figure 1 is a plausible analysis for (1); an alternative analysis would be to take the 4th and 5th sentence as elaborations of and he lavished on those materials an incredibly painstaking technique ....</Paragraph> <Paragraph position="1"> but in this case, as well (and in all other rhetorical structures we could consider) sentences 4 and 5 are satellites of sentence 3. (We have employed the set of rhetorical relations currently used to analyse the ILEX data.) The relation between G&S's and RST's notion of structure has been analysed by, among others, (Moore and Paris, i 993; Moser and Moore, 1996).</Paragraph> <Paragraph position="2"> According to Moser and Moore, the relation can be characterised as follows: an RST nucleus expresses an intention I~; a satellite expresses an intention 18; and I,~ dominates Is. Thus, in (1), the nucleus of the exemplification relation, sentence 3, would dominate the satellite, consisting of sentences 4 and 5. We will make the same assumption here. Hence we can assume that the third sentence in (1) will still be on the stack when processing the 4th and 5th sentences. This would also hold for the alternative rhetorical structures we have considered. 5</Paragraph> </Section> </Section> <Section position="7" start_page="552" end_page="552" type="metho"> <SectionTitle> EXEMPLIFICATION </SectionTitle> <Paragraph position="0"> And if you look at, for instance ....</Paragraph> <Paragraph position="1"> And that particular bangle took HIM ....</Paragraph> </Section> <Section position="8" start_page="552" end_page="554" type="metho"> <SectionTitle> CONSEQUENCE </SectionTitle> <Paragraph position="0"> so that the amount of time he put into the labour ....</Paragraph> <Section position="1" start_page="552" end_page="554" type="sub_section"> <SectionTitle> 4.4 What Goes on the Stack? </SectionTitle> <Paragraph position="0"> We can finally turn to the task of explaining how the global focus is used to resolve long-distance pronominalisations. The simplest explanation consistent with the G&S's framework would be to assume that resolving such pronouns involves searching for the first discourse entity in the focus space stack that satisfies gender and number constraints.</Paragraph> <Paragraph position="1"> Under the assumptions about the discourse structure of examples like (1) just discussed, this explanation would indeed account for that example; there is evidence, however, that additional constraints are involved. The first bit of evidence is that the presence on the focus space stack of an appropriate antecedent does not always make the use of a long distance pronoun felicitous. Consider tile following fi'agment of an article that appeared in The Guardian, January 28, 1995, p.3.</Paragraph> <Paragraph position="2"> (4) Joan Partington, aged 44, from Bolton, Lancashire, has six children. The eldest are two 17-year-old twin boys, one awaiting a heart bypass operation and the other with severe behavioral problems. A 13-year-old son has hydrocephalus. She was living with her husband when Wigan magistrates ordered her to be jailed unless she paid PS5 per week, although he earned only PS70 per week as a part-time postman.</Paragraph> <Paragraph position="3"> anaphoric reference, since centering does not explain how a pronoun can refer to an antecedent two sentences back. Assuming that there is more than one segment in such texts, instead, will turn out to be not just a more plausible assumption about segmentation; it will also give us a simple way to explain the data, The use of he in the last sentence is awkward, even though there is a discourse entity on the focus space stack- the husband- that would satisfy the constraints imposed by the pronoun. This seems to indicate that the elements of a focus space are not all equally accessible.</Paragraph> <Paragraph position="4"> The second relevant bit of evidence concerns the use of proper names in the ILEX corpus. It may happen in the ILEX dialogues that a designer like Jessie King is first mentioned by name in a segment where she is not the main topic of discussion, as in Other jewels in the Bohemian style include a brooch by Jessie King. If this is the case, then when later we're talking about another jewel that King designed, she will have to be introduced again with a full proper name, Jessie King, rather than simply King. If, however, she becomes the 'main topic' of discussion, then later, whenever we talk about her again, we can use reduced forms of her proper name, such as King.</Paragraph> <Paragraph position="5"> Again, this difference is not easy to explain in terms of focus spaces if we assume that all objects in a focus space have the same status.</Paragraph> <Paragraph position="6"> A third class of expressions providing evidence relevant to this discussion are bridging descriptions, i.e., definite descriptions like the door that refer to an object associated with a previously mentioned discourse entity such as the house, rather than to the entity itself (Clark, 1977). Poesio et al. (1997; 1998) report experiments in which different types of lexical knowledge sources are used to resolve bridging descriptions and other cases of definite descriptions that require more than simple string match for their resolution. Their results indicate that to resolve bridging descriptions it is not sufficient simply to find which of the entities in the current focus space is semantically closest to the bridging description: in about half of the cases of bridging descriptions that could be resolved on the basis of the lexical knowledge used in these experiments, the focus spaces contained an entity whose description was more closely related to that of the bridging description than the one of the actual antecedent(s).</Paragraph> <Paragraph position="7"> This evidence about infelicitous pronouns, proper names, and bridging descriptions suggests that the entities in a focus space are not all equally salient.</Paragraph> <Paragraph position="8"> In fact, one could even wonder if we need focus spaces at all; i.e., if Sidner's original proposal - according to which it's just the MSE that goes on the stack, not the whole focus space - is correct. A revision of G&S's theory along these lines- i.e., in which the focus space stack is replaced by an MSE stack- would still explain (1), since the jeweller is clearly the MSE of sentence 3; indeed, all 7 cases of long-distance pronouns found in the ILEX corpus have a previous MSE as their antecedent. But, in addition, this revision would explain the awkwardness of (4): the husband was never an MSE, so it would not be on the stack.</Paragraph> <Paragraph position="9"> A global focus of this type would also give us a way to formulate a restriction on using shortened forms of proper names that would account for the facts observed in the ILEX corpus: reduced NPs are allowed for entities that have been introduced as MSEs, full NPs are needed otherwise. And finally, keeping track of previous MSEs seems essential for bridging descriptions as well: in order to find the reasons for the low performance of algorithms for resolving bridging descriptions entirely based on lexical knowledge, (Poesio et al., 1998) examined the bridging descriptions their corpus to find out their 'preferred' antecedent. 6 They found that the preferred antecedent of a bridging description is a previous MSE in 54 out of 203 cases. In the SOLE COrpUS, 8 OUt of 11 bridging descriptions relate to the MSE.</Paragraph> <Paragraph position="10"> Does this mean, then, that we can get rid of focus spaces, and assume that it's MSEs that go on the stack? Before looking at the data, we have to be clear as to what would count as evidence one way or the other. Even an approach in which only previous MSES are on the stack would still allow access to entities which are part of what Grosz called the IM-PLICIT FOCUS of these MSEs, i.e., the entities that 6As discussed in (Poesio and Vieira, 1998), in general there is more than one potential 'antecedent' for a bridging description in a text.</Paragraph> <Paragraph position="11"> are 'strongly associated' with the MSES. This notion of 'strong association' is difficult to define- in fact, it is likely to be a matter of degree- but nevertheless it is plausible to assume that the objects 'strongly associated' with a discourse entity A do not include every discourse entity B which is part of a situation described in the text in which A is also involved; and this can be tested with linguistic examples, up to a point. For example, whereas definite descriptions like the radiator cap can easily be resolved in a null context to a car, descriptions like the dog can't, as shown by the infelicity of (5d) as a continuation of (5b), even though dogs in cars are not uncommon; some contextual antecedent is needed.</Paragraph> <Paragraph position="12"> (5) a. Mary saw a dark car go by quickly.</Paragraph> <Paragraph position="13"> b. It was a bright, warm day.</Paragraph> <Paragraph position="14"> c. The radiator cap was shining in the sun.</Paragraph> <Paragraph position="15"> d. The dog was enjoying the warmth.</Paragraph> <Paragraph position="16"> The question we have to answer, then, is whether the only information that is available as part of the attentional state is what is 'strongly associated' with one of the previous MSES, or, instead, all of the information mentioned in the text. 7 Now, sentences like (5a) license both bridging descriptions to the car, as in (5c), and to Mary, as in Her hat had become very hot. Whatever we take the MSE of (5a) tO be, it seems implausible to argue that both the bridging description s the radiator cap and Her hat are resolved by looking at the objects 'strongly associated' with that discourse entity. It is much simpler to assume that both Mary and the car are still accessible as part of the focus space constructed to represent the situation described by the text. This also holds for what we have called 'generic' pronouns, as shown by (3), in which they refers to individuals associated with the hotel mentioned in the first sentence, not to the MSE, John. And indeed, Sidner assumed two stacks- one of discourse foci, the other of actor foci. But even this extension would not be enough, because the antecedent of a bridging description is not always an entity explicitly introduced in the text, but can also be a more abstract DISCOURSE TOPIC, by which we 7Notice however that the claim that only MSES go on the stack does not entail that everything else in the text is simply forgotten- the claim is simply that that intbrmation is not available for resolving references anymore; presumably it would be stored somewhere in 'long term memory'. Conversely, the claim that everything stays on the stack would have to be supplemented by some story concerning how information gets forgotten-e.g., by some caching mechanism such as the one proposed by Walker (1996).</Paragraph> <Paragraph position="17"> mean an issue / proposition that can be said to characterise the content of the focus space as a whole. In a corpus analysis done in connection with (Poesio et al., 1997; Poesio et al., 1998), we found that 7 out of 70 inferential descriptions were of this type; in the SOLE corpus, in which 3 out of 11 bridging descriptions behave this way. An example of this use is the description the problem below, that refers to the problem introduced by the first sentence in the text: (6) Solo woodwind players have to be creative if they want to work a lot, because their repertoire and audience appeal are limited .... The oboist Heinz Holliger has taken a hard line about the problem ...</Paragraph> <Paragraph position="18"> Reference to abstract objects in general seem to require maintaining information about the events and situations described by a text on the stack- see, e.g., (Webber, 1991). So, it looks like what we need is something of a compromise between the notion of global focus implicit in Sidner's original proposal and that proposed by G&S.</Paragraph> </Section> <Section position="2" start_page="554" end_page="554" type="sub_section"> <SectionTitle> 4.5 The proposal </SectionTitle> <Paragraph position="0"> The following hypothesis about the global focus and its use in pronoun resolution seems to provide the best account of the evidence we have examined: 1. The global focus consists of a stack of focus spaces, as in G&S's proposal. Each of these focus spaces can be summarised as being 'about' some object / proposition / issueindeed, more than one- for which we will use the term DISCOURSE TOPICS; but, in addition, 2. Each focus space may be optionally associated with a MOST SALIENT ENTITY (MSE) explicitly introduced in the text.</Paragraph> <Paragraph position="1"> 3. The antecedent for a non-generic pronoun is preferentially to be found in the local focus; if none is available, one of the MSEs associated with a focus space on the stack can also serve as antecedent. 8 4. Generic pronouns refer back to the situation described by the current focus space; 5. Bridging descriptions can be related either to an entity in the current focus space, or to an MSE, or to a discourse topic; rThis would explain the difference in reading times observed by (Clark and Sengul, 1979).</Paragraph> <Paragraph position="2"> 6. Definite descriptions can refer back to any entity in the global focus, including discourse topics.</Paragraph> <Paragraph position="3"> The reason for using the term 'optional' in 2 is that whereas focus spaces can always be described as being about something, they are not always associated with a 'most salient entity': e.g., the first sentence in (6) introduces several topics (woodwind players, their need to be creative, etc.) but does not introduce an MSE.</Paragraph> </Section> </Section> class="xml-element"></Paper>