Or Biran

Putting it Simply: a Context-Aware Approach to Lexical Simplification

We present a method for lexical simplification. Simplification rules are learned from a comparable corpus, and the rules are applied in a context-aware fashion to input sentences. Our method is unsupervised. Furthermore, it does not require any alignment or correspondence among the complex and simple corpora. We evaluate the simplification according to three criteria: preservation of grammaticality, preservation of meaning, and degree of simplification. Results show that our method outperforms an established simplification baseline for both meaning preservation and simplification, while maintaining a high level of grammaticality.

Aggregated Word Pair Features for Implicit Discourse Relation Disambiguation

We present a reformulation of the word pair features typically used for the task of disambiguating implicit relations in the Penn Discourse Treebank. Our word pair features achieve significantly higher performance than the previous formulation when evaluated without additional features. In addition, we present results for a full system using additional features which achieves close to state of the art performance without resorting to gold syntactic parses or to context outside the relation.

Identifying Justifications in Written Dialogs By Classifying Text as Argumentative

In written dialog, discourse participants need to justify claims they make, to convince the reader the claim is true and/or relevant to the discourse. This paper presents a new task (with an associated corpus), namely detecting such justifications. We investigate the nature of such justifications, and observe that the justifications themselves often contain discourse structure. We therefore develop a method to detect the existence of certain types of discourse relations, which helps us classify whether a segment is a justification or not. Our task is novel, and our work is novel in that it uses a large set of connectives (which we call indicators), and in that it uses a large set of discourse relations, without choosing among them.

Predicting the impact of scientific concepts using full-text features

New scientific concepts, interpreted broadly, are continuously introduced in the literature, but relatively few concepts have a long‐term impact on society. The identification of such concepts is a challenging prediction task that would help multiple parties—including researchers and the general public—focus their attention within the vast scientific literature. In this paper we present a system that predicts the future impact of a scientific concept, represented as a technical term, based on the information available from recently published research articles. We analyze the usefulness of rich features derived from the full text of the articles through a variety of approaches, including rhetorical sentence analysis, information extraction, and time‐series analysis. The results from two large‐scale experiments with 3.8 million full‐text articles and 48 million metadata records support the conclusion that full‐text features are significantly more useful for prediction than metadata‐only features and that the most accurate predictions result from combining the metadata and full‐text features. Surprisingly, these results hold even when the metadata features are available for a much larger number of documents than are available for the full‐text features.

Detecting Influencers in Written Online Conversations

It has long been established that there is a correlation between the dialog behavior of a participant and how influential he or she is perceived to be by other discourse participants. In this paper we explore the characteristics of communication that make someone an opinion leader and develop a machine learning based approach for the automatic identification of discourse participants that are likely to be influencers in online communication. Our approach relies on identification of three types of conversational behavior: persuasion, agreement/disagreement, and dialog patterns.

PDTB Discourse Parsing as a Tagging Task: The Two Taggers Approach

Full discourse parsing in the PDTB framework is a task that has only recently been attempted. We present the Two Taggers approach, which reformulates the discourse parsing task as two simpler tagging tasks: identifying the relation within each sentence, and identifying the relation between each pair of adjacent sentences. We then describe a system that uses two CRFs to achieve an F1 score of 39.33, higher than the only previously existing system, at the full discourse parsing task. Our results show that sequential information is important for discourse relations, especially cross-sentence relations, and that a simple approach to argument span identification is enough to achieve state of the art results. We make our easy to use, easy to extend parser publicly available.

An Entity-Focused Approach to Generating Company Descriptions.

Finding quality descriptions on the web, such as those found in Wikipedia articles, of newer companies can be difficult: search engines show many pages with varying relevance, while multi-document summarization algorithms find it difficult to distinguish between core facts and other information such as news stories. In this paper, we propose an entity-focused, hybrid generation approach to automatically produce descriptions of previously unseen companies, and show that it outperforms a strong summarization baseline.

Discourse Planning with an N-gram Model of Relations

While it has been established that transitions between discourse relations are important for coherence, such information has not so far been used to aid in language generation. We introduce an approach to discourse planning for conceptto-text generation systems which simultaneously determines the order of messages and the discourse relations between them. This approach makes it straightforward to use statistical transition models, such as n-gram models of discourse relations learned from an annotated corpus. We show that using such a model significantly improves the quality of the generated text as judged by humans.

Mining Paraphrasal Typed Templates from a Plain Text Corpus

Finding paraphrases in text is an important task with implications for generation, summarization and question answering, among other applications. Of particular interest to those applications is the specific formulation of the task where the paraphrases are templated, which provides an easy way to lexicalize one message in multiple ways by simply plugging in the relevant entities. Previous work has focused on mining paraphrases from parallel and comparable corpora, or mining very short sub-sentence synonyms and paraphrases. In this paper we present an approach which combines distributional and KB-driven methods to allow robust mining of sentence-level paraphrasal templates, utilizing a rich type system for the slots, from a plain text corpus.

Human-centric justification of machine learning predictions

Human decision makers in many domains can make use of predictions made by machine learning models in their decision making process, but the usability of these predictions is limited if the human is unable to justify his or her trust in the prediction. We propose a novel approach to producing justifications that is geared towards users without machine learning expertise, focusing on domain knowledge and on human reasoning, and utilizing natural language generation. Through a task-based experiment, we show that our approach significantly helps humans to correctly decide whether or not predictions are accurate, and significantly increases their satisfaction with the justification.