Greg Durrett

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2016-137

August 4, 2016

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-137.pdf

When automated systems attempt to deal with unstructured text, a key subproblem is identifying the relevant actors in that text---answering the "who" of the narrative being presented. This thesis is concerned with developing tools to solve this NLP subproblem, which we call entity analysis. We focus on two tasks in particular: first, coreference resolution, which consists of within-document identification of entities, and second, entity linking, which involves identifying each of those entities with an entry in a knowledge base like Wikipedia.

One of the challenges of coreference is that it requires dealing with many different linguistic phenomenon: constraints in reference resolution arise from syntax, semantics, discourse, and pragmatics. This diversity of effects to handle makes it difficult to build effective learning-based coreference resolution systems rather than relying on handcrafted features. We show that a set of simple features inspecting surface lexical properties of a document is sufficient to capture a range of these effects, and that these can power an efficient, high-performing coreference system.

Our analysis of our base coreference system shows that some examples can only be resolved successfully by exploiting world knowledge or deeper knowledge of semantics. Therefore, we turn to the task of entity linking and tackle it not in isolation, but instead jointly with coreference. By doing so, our coreference module can draw upon knowledge from a resource like Wikipedia, and our entity linking module can draw on information from multiple mentions of the entity we are attempting to resolve. Our joint model of these tasks, which additionally models semantic types of entities, gives strong performance across the board and shows that effectively exploiting these interactions is a natural way to build better NLP systems.

Having developed these tools, we show that they can be useful for a downstream NLP task, namely automatic summarization. We develop an extractive and compressive automatic summarization system, and argue that one deficiency it has is its inability to use pronouns coherently in generated summaries, as we may have deleted content that contained a pronoun's antecedent. Our entity analysis machinery allows us to place constraints on summarization that guarantee pronoun interpretability: each pronoun must have a valid antecedent included in the summary or it must be expanded into a reference that makes sense in isolation. We see improvements in our system's ability to produce summaries with coherent pronouns, which suggests that deeper integration of various parts of the NLP stack promises to yield better systems for text understanding.

Advisors: Daniel Klein

---

BibTeX citation:

@phdthesis{Durrett:EECS-2016-137,
    Author= {Durrett, Greg},
    Title= {Identifying and Resolving Entities in Text},
    School= {EECS Department, University of California, Berkeley},
    Year= {2016},
    Month= {Aug},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-137.html},
    Number= {UCB/EECS-2016-137},
    Abstract= {When automated systems attempt to deal with unstructured text, a key subproblem is identifying the relevant actors in that text---answering the "who" of the narrative being presented. This thesis is concerned with developing tools to solve this NLP subproblem, which we call entity analysis. We focus on two tasks in particular: first, coreference resolution, which consists of within-document identification of entities, and second, entity linking, which involves identifying each of those entities with an entry in a knowledge base like Wikipedia.

One of the challenges of coreference is that it requires dealing with many different linguistic phenomenon: constraints in reference resolution arise from syntax, semantics, discourse, and pragmatics. This diversity of effects to handle makes it difficult to build effective learning-based coreference resolution systems rather than relying on handcrafted features. We show that a set of simple features inspecting surface lexical properties of a document is sufficient to capture a range of these effects, and that these can power an efficient, high-performing coreference system.

Our analysis of our base coreference system shows that some examples can only be resolved successfully by exploiting world knowledge or deeper knowledge of semantics. Therefore, we turn to the task of entity linking and tackle it not in isolation, but instead jointly with coreference. By doing so, our coreference module can draw upon knowledge from a resource like Wikipedia, and our entity linking module can draw on information from multiple mentions of the entity we are attempting to resolve. Our joint model of these tasks, which additionally models semantic types of entities, gives strong performance across the board and shows that effectively exploiting these interactions is a natural way to build better NLP systems.

Having developed these tools, we show that they can be useful for a downstream NLP task, namely automatic summarization. We develop an extractive and compressive automatic summarization system, and argue that one deficiency it has is its inability to use pronouns coherently in generated summaries, as we may have deleted content that contained a pronoun's antecedent. Our entity analysis machinery allows us to place constraints on summarization that guarantee pronoun interpretability: each pronoun must have a valid antecedent included in the summary or it must be expanded into a reference that makes sense in isolation. We see improvements in our system's ability to produce summaries with coherent pronouns, which suggests that deeper integration of various parts of the NLP stack promises to yield better systems for text understanding.},
}

EndNote citation:

%0 Thesis
%A Durrett, Greg 
%T Identifying and Resolving Entities in Text
%I EECS Department, University of California, Berkeley
%D 2016
%8 August 4
%@ UCB/EECS-2016-137
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-137.html
%F Durrett:EECS-2016-137