Computational Textual Inference

1
Computational Textual Inference
RECOGNIZING TEXTUAL ENTAILMENT RTE-2 VENICE,
ITALY April 10, 2006

• Sanda Harabagiu

2
Outline

• Forms of textual entailment
• Paraphrases and Entailment
• Contradictions and entailments
• A Special Case Temporal Inference
• Applications
• Strategies

3
Textual Entailment

• The problem did not originate in the vacuum !!!
• There are many possible way of characterizing the
  forms of textual entailment
• Lauri Karttunen and Annie Zaenen (PARC) have
  proposed a categorization in terms of Logical
  entailment vs. Conversational inference vs.
  Plausible inference vs. Presuppositions
• Lauri Karttunen and Annie Zaenen have also raised
  the issue of Strong implicatives and
  Semi-implicatives
• Textual entailments could also be characterized
  by
• the form of knowledge they employ
• the inference framework that justifies them

4
Entailments and implicative inferences

• Logical entailment
• Many terrorists were killed. Some terrorists
  were killed.
• Conversational inference
• Bush was able to convince McCain to campaign for
  him.
• but Bush chose not to do it.
• Many terrorists were killed. Some terrorists
  were not killed.
• in fact all of them.
• Plausible inference
• Many terrorists were shot. Many terrorist were
  killed.
• Presupposition
• Kerry realized that the campaign was in trouble.
• Kerry did not realize that the campaign was in
  trouble.

5
Strong Implicatives

• In affirmative sentences, strong positive
  implicatives such as manage entail that the
  embedded proposition is true, while strong
  negative implicatives such as fail entail that
  the embedded proposition is false. In negative
  sentences, the polarity of the entailment is
  reversed. Strong implicatives also carry
  presuppositions. (Otherwise they would be devoid
  of any meaning.)
• Kerry managed to hold on to his seat.
• Entails Kerry held on to his seat.
• Presupposes It was difficult for Kerry to hold
  on to his seat.
• Bush didnt manage to find any oil.
• Entails Bush didn't find any oil.
• Presupposes It was difficult for Bush to find
  oil.
• The administration failed to track down the
  perpetrators.
• Entails The administration didn't track down the
  perpetrators.
• Presupposes The administration tried or should
  have tried to track down the perpetrators.
• Bush didnt fail to read a report warning of
  al-Qaida attacks.
• Entails Bush read a report warning of al-Qaida
  attacks.
• Presupposes Bush tried or should have tried to
  read the report.
• Other strong implicative constructions
• Positive bother to, happen to, get around to,
  succeed, take the trouble
• Negative forget to, avoid (-ing), neglect to,

6
Semi-Implicatives

• In negative sentences, positive
  semi-implicatives entail that the embedded
  proposition is false in affirmative sentences
  there is no entailment but there may be a
  "conversational implication" that the embedded
  proposition is true.
• Kerry wasn't able to convince McCain to run with
  him.
• Entails Kerry didn't convince McCain to run
  with him.
• Kerry was able to convince McCain to run with
  him.
• Doesn't entail, strictly speaking, that Kerry
  convinced McCain to run with him. It is not a
  contradiction to say "Kerry was able to convince
  McCain to run with him but chose not to do it."
• However, in the absence of any contradictory
  information, the sentence is misleading if McCain
  was not convinced by Kerry.
• Kerry would have been able to convince McCain to
  run with him.
• In the actual world he wasn't able.
• More semi-implicative constructions
• She didnt have a chance / time / money /
  courage to follow your advice.
• He wasnt bold / clever / strong enough to meet
  the challenge.
• yield a negative entailment under negation, a
  positive conversational implicature in
  affirmative sentences if there is no
  counterindication.
• I was too scared / timid / stupid / distracted
  to do what I promised.
• yield a negative entailment in affirmative
  sentences, a positive conversational implication
  in negative sentences

7
Knowledge used for Textual Entailment

• Textual inference is difficult because of the
  various forms of knowledge that a system needs to
  have available for deriving inference
• Temporal knowledge
• Spatial knowledge
• Causal knowledge
• Commonsense knowledge
• Newsworthy knowledge
• Domain knowledge

8
Examples

• Temporal Knowledge
• T1 Sardar Patel faced imprisonment for the first
  time when he was assisting Gandhiji in the Salt
  Satyagraha.
• H1 Sardar Patel has never been in prison before.
  (PLAUSABLE)
• H2 Sardar Patel was convicted of a crime at
  least once in his life. (TRUE)
• T2 Herbicide use in some areas of the U.S. was
  delayed earlier in the year by heavy rains.
• H Herbicides were used this year in the U.S.
  (TRUE)

9
Examples

• Spatial knowledge
• T1 The unemployed took to the streets of the
  German capital, Berlin, mirroring protests around
  the country.
• H1 The protests took place only in Berlin
  (FALSE).
• T2 John left Venice in the morning, taking the
  10 am flight to London.
• H2 John was in Venice at 8 am. (TRUE)
• H3 John will be in London in the evening
  (PLAUSIBLE).

10
Examples

• Causal Inference
• T Darryl Strawberry recently avoided
  imprisonment when a judge sentenced him to a drug
  treatment center for violating his probation.
• H Darryl Strawberry was sentenced because he
  violated his probation (TRUE).
• Interactions with temporal inference
• H Darryl Strawberry has never been in prison.
  (UNKOWN)

11
Examples

• World Knowledge
• T1 Many cell phones have built-in digital
  cameras.
• H1 Some cell phones can be used to take
  pictures.(PLAUSIBLE the cameras in the cell
  phones must work)
• T2 Mr. Radley ordered a 16 ounce slab of slowly
  roasted Black Angus Prime Rib.
• H2 Radley is a vegetarian. (FALSE Vegetarians
  don't eat meat and people usually intend to eat
  what they order.)

12
Trustworthiness

• Reuters reports that Congress has passed the use
  of force resolution.
• Statement Congress has passed the use of force
  resolution.
• Source Reuters
• Author uncommitted (reports)
• Although the author is noncommittal, the reader
  may choose to take the statement as true if the
  source is trustworthy.
• trustworthy well-informed and honest
• Reuters reports that the UN said on Monday that
  the Iraqis claim that Iraq has fully cooperated
  with the inspectors.

13
Domain Knowledge

• Examples
• T In January-February 1997, China supplied Iran
  with 40,000 barrels of calcium hypochlorite.
• H China provided Iran with decontamination
  materials. (TRUE, calcium hypochlorite is a
  chemical-biological-radiological decontamination
  agent)
• Interaction with world knowledge
• Providing any amount of decontamination materials
  entails that some decontamination materials were
  provided.

14
Our approach to textual entailment in October 2005

• Our approach to textual/lexical entailment seeks
  to benefit from
• The availability of several forms of linguistic
  knowledge
• Good alignment between a question and a text that
  entails it
• Recognition of paraphrases
• Identification of temporal information
• Identification of intentions
• Processing of semantic information (semantic
  frames, named entities)
• EXAMPLE
• Passage Tehran continues to seek considerable
  production technology, training, expertise,
  equipment and chemicals from entities in Russia
  and China that could be used to help Iran reach
  its goal of an indigenous nerve agent production
  capability.
• Question Does Iran want to be a self-sufficient
  producer of CW?
• Answer 1 Yes. Polarity true Force
  plausible Source world
• Because An entity that has a goal of achieving a
  certain state wants to bring about that state.

15
Knowledge Forms

• Features characteristic to eighteen forms of
  knowledge were developed

Negative implication
Intention
RW Knowledge
Positive implication
KW Alternation
Tense/Aspect
Numeric Information
Paraphrasing
Quantification
Date/Time
Possibility
Antonymy
Event Sequence
Uncertainty
Belief Statements
Paraphrase
Speech Act
Pragmatic

• Two independent efforts, students at UTD and the
  researchers at LCC have identified eighteen
  different knowledge forms. The two teams shares
  12 common classes of knowledge forms. Each team
  had at least 6 classes that were unique to this
  effort. Therefore we could not agree on 33 of
  the classes with the other team!

16
The starting point
17
Entailments and Paraphrases

• Techniques used in discovering textual
  paraphrases can be used in determining textual
  entailment.
• These techniques have limitations
• We have used them with promising results for
  recognizing textual contradictions as well

18
Applications

• We have used TE for QA
• We have also used Textual Entailment for a dialog
  system that incorporates the QA
• Entailment at the dialog analysis level
• Entailment at the indexing and retrieval level
• Entailment at the answer justification level

19
Startegies

• Bag-of-words vs. Bag-of-entailments
• It is time to generate some strategies, roadmaps.
• Thank you!