Articles

Uncertainty detection is essential for many NLP applications. For instance, in information re- trieval, it is of primary importance to distinguish among factual, negated and uncertain informa- tion. Current research on uncertainty detection has mostly focused on the English language, in contrast, here we present the first machine learning algorithm …...

Two annotations schemes for presenting the parsed structures are prevalent viz. the constituency structure and the dependency structure. While the constituency trees mark the relations due to positions, the dependency relations mark the semantic dependencies. Free word order languages like Sanskrit pose more problems for constituency parses since the elements …...

While lexicalized reordering models have been widely used in phrase-based translation systems, they suffer from three drawbacks: context insensitivity, ambiguity, and sparsity. We propose a neural reordering model that conditions reordering probabilities on the words of both the current and previous phrase pairs. Including the words of previous phrase pairs …...

In this paper, we present a generic anaphora engine for Indian languages, which are mostly resource- poor languages. We have analysed the similarities and variations between pronouns and their agreement with antecedents in Indian languages. The generic algorithm developed uses the morphological richness of Indian languages. The machine learning approach …...

We address the problem of estimating the quality of Automatic Speech Recognition (ASR) out- put at utterance level, without recourse to manual reference transcriptions and when information about system’s confidence is not accessible. Given a source signal and its automatic transcription, we approach this problem as a regression task where …...

A common site of language use is interactive dialogue between two people situated together in shared time and space. In this paper, we present a statistical model for understanding natural human language that works incrementally (i.e., does not wait until the end of an utterance to begin processing), and is …...

We propose a language modeling (LM) approach incorporating interpolated distanced n-grams in a Dirichlet class language model (DCLM) (Chien and Chueh, 2011) for speech recognition. The DCLM relaxes the bag-of-words assumption and documents topic extraction of latent Dirichlet allocation (LDA). The latent variable of DCLM reflects the class information of …...

We experiment with using different sources of distant supervision to guide unsupervised and semi-supervised adaptation of part-of-speech (POS) and named entity taggers (NER) to Twitter. We show that a particularly good source of not-so-distant supervision is linked websites. Specif- ically, with this source of supervision we are able to improve …...

Social media texts are often written in a non-standard style and include many lexical variants such as insertions, phonetic substitutions, abbreviations that mimic spoken language. The nor- malization of such a variety of non-standard tokens is one promising solution for handling noisy text. A normalization task is very difficult to …...

In the context of Social Media Analytics, Natural Language Processing tools face new chal- lenges on on-line conversational text, such as microblogs, chat, or text messages, because of the specificity of the language used in these channels. This work addresses the problem of Part- Of-Speech tagging (initially for French but …...

We present a novel approach to the problem of multilingual conceptual metaphor recognition. Our approach extends recent work in conceptual metaphor discovery by combining a complex methodology for facet-based concept induction with a distributional vector space model of lin- guistic and conceptual metaphor. In the evaluation of our system in …...

We describe a novel approach to error detection in adjective–noun combinations. We present and release a new dataset of annotated errors where the examples are extracted from learner texts and annotated with error types. We show how compositional distributional semantic approaches can be applied to discriminate between correct and incorrect …...

Derivationally related lemmas like friendN – friendlyA – friendshipN are derived from a common stem. Frequently, their meanings are also systematically related. However, there are also many examples of derivationally related lemma pairs whose meanings differ substantially, e.g., objectN – objectiveN . Most broad-coverage derivational lexicons do not reflect this …...

In this paper, we apply reinforcement learning for automatically learning cooperative persuasive dialogue system policies using framing, the use of emotionally charged statements common in persuasive dialogue between humans. In order to apply reinforcement learning, we describe a method to construct user simulators and reward functions specifically tailored to persuasive …...

Misdiagnosis is a problem in the medical field, often related to physicians’ cognitive errors. Overconfidence is considered a major cause of such errors. Intelligent diagnostic support sys- tems could benefit from understanding how aware physicians are of their performance when they estimate their confidence in a diagnosis (i.e. a physician’s …...

Despite the successes of distant supervision approaches to relation extraction in the news do- main, the lack of a comprehensive ontology of medical relations makes it difficult to apply such approaches to relation classification in the medical domain. In light of this difficulty, we propose an ensemble approach to this …...

This paper presents the first experiments on identifying implicit discourse relations (i.e., relations lacking an overt discourse connective) in French. Given the little amount of annotated data for this task, our system resorts to additional data automatically labeled using unambiguous connec- tives, a method introduced by (Marcu and Echihabi, 2002). …...

In this paper we study how to summarize travel-related information in forum threads to gener- ate supplementary travel guides. Such summaries presumably can provide additional and more up-to-date information to tourists. Existing multi-document summarization methods have limita- tions for this task because (1) they do not generate structured summaries but …...

In this paper we introduce a novel single-document summarization method based on a hidden semi-Markov model. This model can naturally model single-document summarization as the optimization problem of selecting the best sequence from among the sentences in the input doc- ument under the given objective function and knapsack constraint. This …...

We cast multi-sentence compression as a structured prediction problem. Related sentences are represented by a word graph so that summaries constitute paths in the graph (Filippova, 2010). We devise a parameterised shortest path algorithm that can be written as a generalised linear model in a joint space of word graphs …...