English. We investigate the connection between lexical opposition and discourse relations, with a focus on the relation of contrast, in order to evaluate whether opposition participates in discourse relations.1 Through a corpus-based analysis of Italian documents, we show that the relation between opposition and contrast is not crucial, although not insignificant in the case of implicit relation. The correlation is even weaker when other discourse relations are taken into account.
Italiano. Studiamo la connessione tra l’opposizione lessicale e le relazioni del discorso, con attenzione alla relazione di contrasto, per verificare se l’opposizione partecipa alle relazioni del discorso. Attraverso un’analisi basata su un corpus di documenti in italiano, mostriamo che la relazione tra opposizione e contrasto non e` cruciale, anche se non priva di importanza soprattutto per i casi di contrasto implicito. La correlazione sembra piu` debole se consideriamo le altre relazioni del discorso.
This paper focuses on lexical opposition and
discourse contrast. We define opposition as the
relation between two lexical units that contrast with
each other with respect to one key aspect of their
meaning and that are similar for all the other
aspects (e.g. to increase / to decrease, up / down).
On the other end, we consider discourse contrast
as the relation between two parts of a coherent
1Part of this research has already been published in the
first author Ph.D. thesis
In the following example, a contrast relation is identified between the two arguments in square brackets; two opposite terms are found in the arguments of the relation and are underlined. (1) [The price of this book increased], while [the price of that one decreased.]
Despite the two relations are per se independent, the example shows how opposition can participate in contrast; in fact, the opposites to increase / to decrease convey the difference based on which the two mentioned entities (i.e., the books) are compared, leading to a contrast.
Indeed, opposition can be found in the context of other discourse relations (e.g. in the temporal relation “Before the decrease of the demand, an increase of the prices was registered”), and discourse contrast can be conveyed through other strategies (e.g. negation and synonyms “Although the price decreased; the demand did not fall” or incompatibility “She has blue eyes, he has green eyes”).
However, our analysis focuses on opposition
and contrast, and starts with the observation that
both linguistic phenomena involve two elements
that are similar in many aspects, but that differ in
others (Section 2). This similarity have already
been considered by works in the computational
field, in which opposition is used as a feature for
identifying contrast, and viceversa (Section 3). In
this paper, we investigate the behaviour of
opposition in the context of a contrast relation adopting
a corpus-based approach (Section 4). In
particular, we study the opposition-contrast intersection
by observing how frequently opposites are found
in the arguments of a contrast relation in
ContrastIta Bank
Our definition of opposition in mainly based on
the study of Cruse (1986): according to the author,
opposition indicates a relation between two terms
that differ along only one dimension of meaning:
in respect to all other features, they are identical
This definition has some overlap with those
proposed for discourse contrast in two of the most
important frameworks focused on the study of
discourse relations: Rhetorical Structure Theory
Both opposition and discourse contrast thus involve comparing two elements that are similar in many aspects, but that differ in others; this holds at the lexical level for opposition and at the discourse level for contrast. 3
In the area of NLP, the co-occurrence of the opposition and contrast has been considered, for instance, by Roth and Schulte Im Walde (2014), who use what they call discourse markers that typically signal a discourse relation, e.g.but, for distinguishing paradigmatic relations, including opposition.
Other contributions in the same area use lexical
opposition as feature for detecting contrast. As an
example, Harabagiu et al. (2006) base the
identification of contrast on the opposition relation, given
that in some examples “[..] the presence of
opposing information contributes more to the
assessment of a CONTRAST than the presence of a cue
phrase”, such as but or although
Marcu and Echihabi (2002) create a system to
identify relations of contrast under the
hypothesis that some lexical item pairs can “provide
clues about the discourse relations that hold
between the text span in which the lexical items
occur”. In a cross-lingual evaluation for English and
Swedish,
On the contrary, Spenader and Stulp (2007) give evidence that opposition is not a strong feature for contrast. In particular, they calculate the cooccurrence of opposite adjectives in the contrast relations marked or non-marked by but in a corpus. The authors show that opposition is not common in cases of explicit contrast conveyed by but, and it is also not very frequent in cases of nonbut marked contrast. In a similar way, we intend to evaluate whether opposition is a key feature for contrast, or for other discourse relations. 4
We carry on our investigation in Contrast-Ita Bank
(CIB)
To evaluate the role of opposition in the context of a contrast, we manually annotated two opposites opposite1 and opposite2, when the former is part of Arg1 and the latter is part of Arg2. For instance, in Example 1 “The price of this book increased” is Arg1 and “the price of that one decreased” is Arg2, and we marked ‘increased” as opposite1 and “decreased” as opposite2.
In this manual exercises, we did not limit our
annotation to prototypical opposites
(2) [Andrew Smith ha rassegnato le dimissioni ieri], nonostante [i tentativi del premier Tony Blair di convincerlo a rimanere]. 4
In the example, the light-verb construction rassegnare le dimissioni (Eng.‘to resign’) is considered as the opposite of rimanere (Eng.‘to remain’) and the two are found respectively in the two arguments of the contrast relation, conventionally reported in square brackets.
Furthermore, we include in the annotation also ‘opposites in context’, that is, pairs of terms that are not intuitively considered opposite but are in an opposition relation in the specific context in which they appear, as it happens in Example 3. (3) [Sul Nuovo Mercato, Tiscali perde lo 0.05% a 2,23], [E. Biscom sale dell’1,09% a 41,44]. 5 The two terms perdere and salire (Eng. ‘to lose x’, ‘to fall by x’) are semantically opposite in the 3The presence of one type of relation does not exclude the other.
4Eng.:[Andrew Smith resigned yesterday,] despite [Prime Minister Tony Blair’s attempts to persuade him to stay.] 5Eng.:[On the New Market, Tiscali looses 0.05% to 2.23], [E. Biscom rises by 1.09% to 41.44]. specific context of Example 3: they are used in their sense of ‘loosing (some value)’ and ‘increasing (of some value)’. 5
We study the connection between opposition and contrast observing the co-occurrence of the two linguistic phenomena and analyzing whether opposition participates in creating contrast. 5.1
Co-occurrence of the two relations Out of the 372 contrast relations annotated in CIB, we identified a total of 23 cases in which opposites are present in the arguments of a contrast relation6.
Table 1 shows that opposition is present both when contrast is conveyed explicitly by mean of a connective (as by nonostante in Example 2), and when there is no such element (Example 3); however, there is a higher occurrence when the relation is implicit (16% vs 5.2%). With respect to the types of opposition, it occurs both when CONTRAST or CONCESSION have been marked (Examples 3 and 2 respectively), but it is more frequent with the type CONTRAST (9.2% vs 2.5%).
Senses Contrast Concession Both
Types Explicit Implicit 7 4 6 0 5 1 tot 18 5 % over tot 5.2%(/341) 16% (/31) tot % over tot 11 9.2%(/102) 6 2.5% (/234) 6 16.6% (/36) 23 We conducted a deeper investigation in order to evaluate whether the opposites in the arguments of a contrast relation actually contribute to it.
In Example 4 opposition triggers the contrast relation.
(4) [uno dei due e` ricco di cellule staminali], [l’ altro ne e` povero].7
In this case (and in Examples 2 and 3), the contrast relation holds because two entities (e.g. ‘one’, ‘the other’) that share a property (i.e. ‘to 6We manually recognized 20 relations; other 3 were identified ad posteriori applying the methodology described in Section 6.
7Eng.:[one is rich in stem cells],[the other is poor of them.] have stem cell’) are compared with respect to different values that this property takes (i.e. ‘to be rich of them’, ‘to be poor of them’): the different values can be expressed through opposites (i.e. ricco/povero).
Other examples includes case in which the contrast relation stem from a comparison between two values of a property assigned to the same entity, as happens for the example in Example 5.
(5) Il commercialista [doveva essere il cavaliere bianco chiamato a salvare la Chini] e, invece, [e` stato quello che l’ ha affossata].8
In the example, the contrast arises from the comparison between the opposite roles of the participant: to save (something) / to ruin (something).
Opposition is central for the discourse contrast in these examples. This is not the case for Example 6, for which the opposition does not act as a source for the discourse contrast relation. (6) [A dispetto degli sforzi della pubblica amministrazione..], [gli investimenti privati in termini di istruzione sono ancora bassi.]9
In the example, the opposite adjectives pubblico / privato (Eng. ‘private / public’) are attributes of two entities involved: one can say that the participants do have opposite characteristics. However, the contrast relation does not stem from this opposition; rather, it is based on the comparison between the ‘positive efforts’ on the one hand and the ‘low investments’ on the other hand.
Out of 23 cases, in 17 opposites are crucial for the contrast relation while in 6 they do not affect the contrast relation. It seems that when opposites appear in the context of a contrast relation they frequently contribute to the phenomena.
We also performed an inter annotator agreement exercises among two annotators to understand whether to distinguish cases in which opposition contributes in conveying the discourse relation (and cases in which they do not) is an easy operation.10 We register disagreement in 3 cases 8Eng.: The accountant [was supposed to be the white knight designated to save the Chini] and, on the contrary, [he has been the one that ruined it.]
9Eng.: [Despite public administration efforts.], [private investments in terms of education are still low.]
10One annotator is an author of this paper, the second annotator, who has some familiarity with linguistic tasks, was provided with simple oral instructions through which we ask her to judge the contribution of the opposites when in the context of a contrast relation. We acknowledge Enrica Troiano for collaborating as second annotator. out of 20, that corresponds to a Dice’s coefficient of 85%. After a reconciliation step, in which annotators compared their annotations, and could revise their decisions, two cases were solved, while a third, reported in Example 7 remained. (7) [A decorrere da domenica 12 entra in vigore il nuovo orario invernale per il servizio extraurbano e la Trento - Male`.] [Da luned`ı 13 entra invece in vigore il nuovo orario invernale 2004 / 2005 per il servizio urbano di Trento e Rovereto.] 11
In this case, one annotator considered that the contrast among the two situations described in the arguments of the discourse relation originates from the opposites suburban / urban. Conversely, the other annotator recognized the different dates of entering into force of the two service (i.e. Sunday 12 vs Monday 13) as the source of the resulting discourse contrast. 6
We performed a further analysis evaluating cases of opposites in other discourse relations. We carried on this investigation inspecting the entire CIB corpus and adopting an external resource in which opposites are registered12. We automatically retrieved from the corpus pairs of opposites in a windows of 25 token13. We retrieved 152 cases that we manually analyzed considering: whether the two opposites appear in their opposite sense (e.g. the verbs andare / tornare are opposite as far as the first verb is not consider as a modal) - data are reported in the second column of Table 2-, and if so: whether they are somehow related in the text or not (e.g. in e` subentrato un fatto nuovo, determinato dal fatto che i vincitori del vecchio regime non.. the two opposites properties are of two unrelated entities while in proposte ufficiali o ufficiose, the two opposites are in a coordinating relation) - data are 11Eng.: [Starting from Sunday 12 the new winter timetable for the suburban service and for the Trento - Mal enters into force.][From Monday 13 instead the new winter timetable 2004 / 2005 for the urban service of Trento and Rovereto enters into force.]
12Dizionario dei Sinonimi e dei Contrari - Rizzoli Editore, http://dizionari.corriere.it/dizionario sinonimi contrari 13The number was set observing that opposites were found at a maximum distance of 24 tokens in contrast relations. reported in the third column of Table 2. If the opposites are related: whether they are in the arguments of a discourse relation, as in Example 4 - fourth column of the table.
Results show that in a large number of pairs the two opposites are not actually used in their opposite sense (52 cases = 152 - 100) or are not related in the text (28 cases = 100 - 72). The opposites are found in the arguments of a discourse relation just in 18 cases (11.8 % of the total), suggesting that lexical opposition is not an indicator for the presence of a discourse relation.
A further analysis brought us to investigate also in which discourse relations opposites are involved, following the PDTB classification.14 We also investigated if opposition is central for these relations. Data are reported in Table 3.
From Table 3, we see that opposition co-occurs with different discourse relations, especially Conjunction, but in a more limited number of cases with respect to contrast.15
Moreover, comparing the first and the third column of the table, it can be noticed that, as it happens for discourse contrast (see Section 5.2), opposition is not always contributing to the discourse relation itself, meaning that it does not play central role in conveying the relation. As an example, compare Example 8 in which opposition is judged as central, with Example 9 in which it is not.
14The complete list of the PDTB 3.0 relations can be found
in
15The data for CONTRAST and CONCESSION are part of the ones reported in Table 1, which consider also multi-token expressions and ‘opposites in context’. (8)
Sabato [partenza alle 7.01] ed [arrivo alle 19.36.]16 (9) [..il gruppo ha proseguito l’opera di riorganizzazione societaria], [mettendo un po’ d’ ordine nelle partecipazioni non legate al core business delle singole controllate..]17
In the Conjunction relation of Example 8, the two opposite terms indicate the (opposite) events that are coordinated via the conjunction e. In Example 9 (a case of EXPANSION.Level-of-detail relation), the two opposites are somehow related (i.e. the group is operating for the singles subsidiaries), but they are not central for the relation, which is determined by the two events: proseguire l’opera and mettendo [..] ordine. 7
Through the annotation of opposites in the arguments of contrast relations in Contrast-Ita Bank, we aim at providing new insights over the role of opposition in discourse contrast. Overall, we register 23 cases of opposition over 372 contrast relations in our dataset. This number is not high and one we can expect the number to be higher in a larger dataset. However, this limited number suggests that the presence of opposites is not an impacting feature for the identification of contrast relation in the Italian language. It is, however, quite frequent for implicit relations, suggesting that the use of opposition can be a strategy to convey contrast when there is a lack of a connective (such as but or however) that lexicalizes the relation. Moreover, we show that also the co-occurrence of opposition and other discourse relations is low. Despite, in related work opposition has been used as a feature for identifying contrast, the result of our investigation suggests that opposition does not appear to be a strong informative feature and this can possibly lead to a decrease in precision in the process of identifying contrast (i.e., many false positives are expected).
Further and symmetrical work includes the classification of the phenomena that can lead to contrast.
16Eng.: On Saturday, [departure at 7.01] and [arrival at 19.36.]
17Eng.: [.. the group has continued the work of corporate reorganization], [putting some order in the shareholdings that not tied to the core business of the single subsidiaries..]