Lecture 6

Question 1

Summary Of Discourse-Level NLP Tasks

Answer 1

Uncovering discourse structure
(discourse segmentations, discourse
relations, text coherence)

Uncovering document structure
* Recognizing known structure, for
example, abstracts
* Organizing documents according
to known structure

Conducting named entity resolution
across discourse elements

3

Question 2

Discourse Segmentation

Answer 2

Documents are automatically separated into passages, sometimes called fragments, which are different discourse segments
* Discourse segments can inform semantic interpretation of
document

Question 3

Discourse Segmentation - Techniques

Answer 3

Techniques to separate documents into passages include
* Rule-based systems based on clue words and phrases
* Probabilistic techniques to separate fragments and to identify discourse segments
* Lexical cohesion to identify fragments (TextTiling)

Question 4

Lexical Chains: Semantically Related Words

Answer 4

words that refer to the original:
the “book” was taken. “It” was valuable.

Question 5

Relatedness == Cohesion != Coherence

Answer 5

Any document can be viewed as a set
of lexical chains: Clusters of words
based on semantic similarity; but
chains by themselves do not
guarantee coherence

Question 6

Relatedness == Cohesion != Coherence

Answer 6

A multi-sentence sequence becomes
more than a random set of
independent utterances:
* To the extent that semantically similar
noun phrases are used, or that
coreference connects noun phrases
across sentences (cohesion)
* And to the extent that dissimilar noun
phrases are “pragmatically” connected
through actions (coherence)

Question 7

Relatedness == Cohesion != Coherence

Answer 7

Coherent
Locally Incoherent
Topically Incoherent

Question 8

Discourse Structure

Answer 8

Human discourse often exhibits structures that are intended to indicate common experiences and respond to them

Question 9

Discourse Relations

Answer 9

How adjacent text segments are logically connected to each other. The rhetorical
structure of the text

Question 10

Rhetorical Structure Theory

Answer 10

– a theory of text organization created in the 1980s
* Text units as nuclear and satellites
* Three categories of relations:

subject matter relations,
presentational relations,
multinuclear relations

Question 11

Discourse Markers

Answer 11

Many rhetorical relations can be indicated by particular words or
phrases (from Biran and Rambow, 2012)
* But many of these words are ambiguous as they can be used for
other functions in text.

Question 12

Entity Resolution

Answer 12

is an ability of a system to recognize and unify variant references to a single entity.

Question 13

Coreference: A Critical Discourse Level Task

Answer 13

Anaphora - references (he, his, there) to previous text:
* “Doctor Foster went to Gloucester in a shower of rain.
He stepped in a puddle right up to his middle and never went there again.

Question 14

Coreference: A Critical Discourse Level Task

Answer 14

Cataphora - references to future text:
* If you want them, there are cookies in the kitchen

Question 15

Coreference: A Critical Discourse Level Task

Answer 15

Substitution - a more general word serves same function as the item for which it is substituted.
* These biscuits are stale. Get some fresh ones.

Question 16

Coreference: A Critical Discourse Level Task

Answer 16

Ellipsis - something left out, but implied
* Joan brought some roses and Kate _ some sweet peas.

Question 17

Coreference: A Critical Discourse Level Task

Answer 17

The referent for a referring phrase is
found by the resolution algorithm
among the candidates, previous noun
phrases. Clues will involve people vs.
objects and single vs. plural.

Question 18

Generic Algorithmic Approach to Coreference

Answer 18

1. Naively identify all referring phrases for resolution:
   * all Pronouns
   * all definite NPs
   * all Proper Nouns

Question 19

Generic Algorithmic Approach to Coreference

Answer 19

2. Filter out things that look referential but are not
   * geographic names, the United States
   * Pronouns without actual meaning:
   * pleonastic “it”, e.g. it’s 3:45 p.m., it was cold
   * non-referential “it”, “there”
   * it was essential to understood,
   * there seems to be a mistake

Question 20

Generic Algorithmic Approach to Coreference

Answer 20

3. Identify Referent Candidates
   * Potential Reference Candidates:
   * All noun phrases are considered potential
   referent candidates.
   * A referring phrase can also be a referent
   for a subsequent referring phrases,
   Example: (omitted sentence with name
   of suspect)
   He had 300 grams of plutonium 239 in his
   baggage. The suspected smuggler denied
   that the materials were his.
   (chain of 4 referring phrases)
   * All potential candidates are collected in a
   table collecting feature info on each
   candidate.

Question 21

Generic Algorithmic Approach to Coreference

Answer 21

4. Collect Information of features that are used to define between a referring phrase and each candidate
   * Number agreement: plural/singular/neutral
   * Exceptions: some plural or group nouns can be referred to by either it or they
   IBM announced a new product. They have
   been working on it …
   * Gender agreement - animate objects as she/he, or inanimate objects as it
   * Person agreement - First and second person pronouns: “I”, “you; Third person pronouns
   * Grammatic role: candidates in a subject position versus referents in object position
   * Recency/Closeness: The closer a referent is to a candidate, the more likely the link
   * Reflexiveness (e.g., Ted paid himself)

Question 22

Generic Algorithmic Approach to Coreference

Answer 22

Train a classifier over an annotated corpus to identify which candidates and
referring phrases are in the same coreference group
* Typical Evaluation results are on the order of F-measure of 70 for overall
coreference, with generally higher precision than recall
* Pronoun coreference resolution by itself is much higher scoring, usually over
90%.

Question 23

Topic Modeling

Answer 23

Examination of patterns in the given text(or corpus) at the semantic level by
extracting topics from texts.

Topic: A list of words that occur in statistically meaningful ways (for the computer)

Text: Unstructured text such that no computer-readable annotations available that indicate the semantic meaning of the words in the text

Question 24

Topic Models

Answer 24

Topic Modeling takes a corpus and looks for sets of similar words across the collection (the topics) in such a way that each document can be represented by one or more topics

Question 25

Topic Modelling - LDA
(Latent Dirichlet Allocation)

Answer 25

An unsupervised method that models
documents and topics based on Dirichlet
distribution
- each document is considered to be a
distribution over various topics and each topic is modeled as a distribution over words.

Question 26

Domain knowledge

Answer 26

α:
* a low α value: more weight on having each document being composed of only a
few dominant topics,
* a high α value: more weight on having each document being composed of a
relatively larger set of topics.
* β:
* a low β value: more weight on having each topic being composed of only a few
dominant words.
* a high β value: more weight on having each topic being composed of a relatively
larger set of topics

Question 27

Pragmatics

Answer 27

Pragmatics is considered the highest level of natural language understanding and as such is the most challenging for computational approaches. Pragmatics is concerned with the actual meaning of words in the situational context. The implication is that world knowledge
plays a keystone role in enabling an accurate interpretation of an utterance.

Question 28

Overview of Pragmatics

Answer 28

• Pragmatics takes a functional perspective
  – how we use language to achieve things
  in the real world
• One goal is to explain how extra meaning
  is read into utterance without actually
  being encoded in them – usually through
  the construction of world knowledge from
  another source (i.e., previously
  encountered and modeled text,
  ontologies, thesauri, etc.)

Question 29

Overview of Pragmatics

Answer 29

Of prime interest for question answering,
dialog engines, natural language
generation, and human-computer
interactions through conversational agents

Question 30

Overview of Pragmatics

Answer 30

• Many perspectives have been
  advanced to describe and predict
  properties of human conversations
• Gricean Maxims
• Dialogue Act Theory
• Speech Act Theory
• Conversational Structure Analysis

Question 31

Overview of Pragmatics

Answer 31

• From a computational perspective,
  we want to be able to recognize
  and segment each dialog act and
  then make sense of it by
  recognizing speaker intent

Question 32

Four Gricean Maxims

Answer 32

The Maxim of Quality - make your contribution that is true
* Do not say what you believe to be false.
* Do not say that for which you lack adequate
evidence.

The Maxim of Quantity - make your contribution as informative as is required for the current
purpose of the conversation, but no more
informative than that (i.e., no excess information)

The Maxim of Relevance - Utterances should be pertinent to conversational purpose

The Maxim of Manner - Be clear, avoid obscurity,avoid ambiguity, be brief, be orderly

Question 33

Conversational Implicatures

Answer 33

When speaker is observing the
Gricean maxims directly, she will rely
on listener to amplify what she is
saying by some straightforward
inferences, called implicatures
* Example:
* A:Makes statement / asks question
* B:Responds, but on the surface, fails to
answer the question
* A:Assumes B is being co-operative;
makes inferences in order to maintain
assumption that B is being co-operative

These inferences are “conversational
implicatures”

Question 34

Word Meanings

Answer 34

• Usually given by online lexicon such as WordNet, including:
• Word with senses

Question 35

Dialogue Act Theory

Answer 35

In computational linguistics, more detailed
systems attempt to explain not only the
informative aspects of conversations, but the dialogue control aspects of an utterance
* Dialogue Act (DA): is “the combination of a communicative function and a semantic
content”, where the former is “the way in
which dialogue participants use information to change the context.” (Bunt, 2000)
* DA classification: the task of classifying an utterance with respect to the function it
serves in a dialogue, i.e. the act the speaker is performing.

Question 36

Speech Act Theory

Answer 36

Three Levels of Speech Acts affecting the
social reality of the speaker and listener:

Locutionary – proposition of speech act
* The literal meaning of the sentence
(what we’ve been working on in NLP)
Illocutionary – intention of speech act

• The act of asking, answering, promising,
  etc. in uttering a sentence
  Perlocutionary – consequences of speech
• The (often intentional) production of
  certain effects upon the feelings,
  thoughts, or actions of the addressee

Question 37

Taxonomy of Illocutionary Acts’ Intentions

Answer 37

• Assertives – commit the speaker to
  something’s being the case – suggest, swear, boast, conclude
• Directives – attempts by speaker to get
  listener to do something – ask, order, request, invite, advise
• Commissives – obligate oneself to future
  course of action – promise, plan, vow, oppose
• Expressives – share psychological state of
  speaker about something – apologize,
  deplore, thank
• Declarations – bring about a different state of the world as a result of the utterance – resign, marry