The document discusses the development of a maximum entropy model to identify temporal relations in Italian through the use of temporal prepositions. A corpus study involving a large dataset aims to better extract implicit temporal information essential for natural language processing applications. The findings highlight significant features influencing the correct tagging of temporal relations, suggesting future work on integrating these models into comprehensive systems for processing temporal information.

1. Temporal Relations with Signals: the Case of Italian Temporal Prepositions Tommaso Caselli , Felice dell’Orletta and Irina Prodanof {firstname.lastname@ilc.cnr.it} ILC-CNR, Pisa 16 th International Symposium on Temporal Representation and Reasoning TIME 2009 Bressanone/Brixen, July 24 2009

2. Different approach Application oriented NLP techniques Focus on: intuitions, knowledge and strategies people use in order to place events in time order events (encoding and decoding) Query texts (corpora) and NOT structured knowledge Introduction

3. Outline: Motivations Temporal Signals in Italian: Theoretical background Methodology Corpus Study A Maximum Entropy Model Feature Identification Evaluation and Results Conclusion and Future Work

4. Motivations Recovering temporal relations in text/discourse is essential to improve the performance of many NLP systems (O.D-Q.A., Text Mining, Summarization, Reasoning) Most temporal information in text/discourse is only IMPLICITLY stated Need to develop procedures to maximize the role of the various sources of information Temporal prepositions are a partially explicit source of information. Determinig their meaning is part of a strategy to improve the extraction of temporal information

5. Motivations (2)

6. Theoretical Background SIGNAL = cover term for a homogeneous class of words which express relations between textual entities EXPLICIT = self-evident and stable meaning; Rel (X, Y) IMPLICIT = abstract meaning which gets specialized in the co-text; Rel ( λ (X), λ (Y)) Temporal signals express temporal relations. Temporal signals can occur in 3 types of constructions involving temporal entities: temporal expression – temporal expression eventuality – temporal expression eventuality - eventuality

7. Corpus Study: Data To identify a large set of temporal signals realized by prepositions we have conducted a corpus study: 5 million shallow parsed word corpus (from the PAROLE corpus) all PP chunks with their left and right contexts have been automatically extracted and imported into a database structure automatically generated DB augmented with ontological information from the SIMPLE/CLIPS Ontology, by associating the head noun of each PP chunk to its ontological type extraction of the noun head corresponding to type TIME + postprocessing to exclude false positives (e.g. incubation , school …)

8. Corpus Study (2) Temporal relations coded by implicit signals: annotation of temporal relations by means of paraphrase tests e.g. [sono stato sposato] per [4 anni] ( I’ve been married for four years ) The state of “being married” EQUALS four years 499 occurrences of construction of the type “eventuality + signal + temporal expressions” 9 temporal relations (compliant with TimeML and ISO-TimeML): overlap , simultaneous, before, after, no tlink, begin, end, before_ending , equals the most frequent temporal relation/implicit signal is assumed to be the prototypical meaning of the signal

9. Feature Identification The corpus study together with theoretical statements have led to the identification of 16 features: PREP: the signal lemma 3 sets of co-textual feature: information about temporal expression information about the eventuality local contextual information

10. Feature Identification – Temporal Expressions Temporal expression features: Ontological status: INSTANT, INTERVAL Type of temporal expressions (TIMEX): DATE: August 3 ; 1968 ; 01/12/1980 … DURATION: 3 hours ; the last quarter … SET: once every year … TIME: 3 o’ clock ; (in) the morning … Presence of a quantifier: QUANTIFIER

11. Feature Identification - Eventuality Eventuality features: Lemma (POTGOV_head); POS of the eventuality: VERB, NOUN Presence of negations (NEGATION) Verb diatesis (DIATESIS) Tense: PRESENT, IMPERFECT, FUTURE, PAST, INFINITIVE (Viewpoint) Aspect: IMPERFECTIVE, PERFECTIVE, PROGRESSIVE, NONE Lexical Aspect (AKTIONSAART): TRANSITION, PROCESS, STATE

12. Feature Identification – Local context Local context features: features which accounts for the presence of further signals in the local context which influence the identification of the Rel value of the signal in analysis FOLLOWED_SIGNAL+TIMEX PRECEED_SIGNAL+TIMEX FOLLOWED_SIGNAL+EVENT

13. Building a M.E. Model Feature annotation: manually conducted by one annotator + one of the author. 1000 instances of constructions of the type “eventuality + signal + timex” two interlinked criteria: semantic transparency of the signal + relative frequency of the signal in the 5 million shallow parsed corpus Assigning the right temporal relation is (in essence) a tagging task.  Maximum Entropy algorithm: it provides a suitable solution to identify the set of possible values for each signal on the basis of the conditional probability distribution. No a priori constraints must be met other than those related to a set of features f i (a, c) of a context C, whose distribution is derived from the training data.

14. Evaluation The data set has been split in test (100) and training (900) data 8 different models have been created to discover the most salient features. 10- cross fold validation/model. All models outperforms the baseline  relevance of the features

15. Evaluation (2) PREP INTERVAL INSTANT POTGOV_head VERB NOUN DIATESIS NEGATION AKTIONSAART FOLLOWED_SIGNAL+TIMEX PRECEED_SIGNAL+TIMEX FOLLOWED_SIGNAL+EVENT TENSE ASPECT TIMEX QUANTIFIER 10 Feature Model Performance = 90% surface-based features good performance without the AKTIONSAART feature

16. Evaluation (3) PREP, INTERVAL, INSTANT, FOLLOWED_SIGNAL+TIMEX, PRECEED_SIGNAL+TIMEX, FOLLOWED_SIGNAL+EVENT, TIMEX, QUANTIFIER 89.8% 8 features PREP, INTERVAL, INSTANT, AKTIONSAART , FOLLOWED_SIGNAL+TIMEX, PRECEED_SIGNAL+TIMEX, FOLLOWED_SIGNAL+EVENT, TIMEX, QUANTIFIER 89.8% 9 features Features Performance Model

17. Evaluation (3) PREP, INTERVAL, INSTANT, TIMEX, QUANTIFIER 87.6% 5 features PREP, INTERVAL, INSTANT, FOLLOWED_SIGNAL+TIMEX, PRECEED_SIGNAL+TIMEX, FOLLOWED_SIGNAL+EVENT, TIMEX, QUANTIFIER 86.8% 7 features PREP, INTERVAL, INSTANT, AKTIONSAART, FOLLOWED_SIGNAL+TIMEX, PRECEED_SIGNAL+TIMEX, FOLLOWED_SIGNAL+EVENT, TIMEX 85% 8 features (No QUANTIFIER) Features Performance Model

18. Conclusion & Future Work Mismatch between linguistic theory and features salience Observations on the features: 5 core features: PREP, INSTANT, INTERVAL, TIMEX, QUANTIFIER (5 feature model) AKTIONSAART influence in this task is almost null. It could be reduced with a set of features more surface-based e.g. presence of D.O., definiteness, cardinality, type of subject… the remaining features could be activated in particular linguistic context and with particular signals; e.g. TENSE, ASPECT and AKTIONSAART (ot its subsitutes) with the signal IN; the local context features with the signals DA, A and TRA. Integration of the M.E. Model into a complete automatic system for temporal processing of text/discourse

19. Thanks