Rafael E. Banchs

Bio: Rafael E. Banchs is an academic researcher from Nanyang Technological University. The author has contributed to research in topics: Machine translation & Example-based machine translation. The author has an hindex of 25, co-authored 144 publications receiving 2940 citations. Previous affiliations of Rafael E. Banchs include Polytechnic University of Catalonia & Institute for Infocomm Research Singapore.

N-gram-based Machine Translation

Abstract: This article describes in detail an n-gram approach to statistical machine translation. This approach consists of a log-linear combination of a translation model based on n-grams of bilingual units, which are referred to as tuples, along with four specific feature functions. Translation performance, which happens to be in the state of the art, is demonstrated with Spanish-to-English and English-to-Spanish translations of the European Parliament Plenary Sessions (EPPS).

IRIS: a Chat-oriented Dialogue System based on the Vector Space Model

Abstract: This system demonstration paper presents IRIS (Informal Response Interactive System), a chat-oriented dialogue system based on the vector space model framework. The system belongs to the class of example-based dialogue systems and builds its chat capabilities on a dual search strategy over a large collection of dialogue samples. Additional strategies allowing for system adaptation and learning implemented over the same vector model space framework are also described and discussed.

The Structure of Political Discussion Networks: A Model for the Analysis of Online Deliberation:

Abstract: This paper shows that online political discussion networks are, on average, wider and deeper than the networks generated by other types of discussions: they engage a larger number of participants and cascade through more levels of nested comments. Using data collected from the Slashdot forum, this paper reconstructs the discussion threads as hierarchical networks and proposes a model for their comparison and classification. In addition to the substantive topic of discussion, which corresponds to the different sections of the forum (such as Developers, Games, or Politics), we classify the threads according to structural features like the maximum number of comments at any level of the network (i.e. the width) and the number of nested layers in the network (i.e. the depth). We find that political discussion networks display a tendency to cluster around the area that corresponds to wider and deeper structures, showing a significant departure from the structure exhibited by other types of discussions. We propose using this model to create a framework that allows the analysis and comparison of different internet technologies for the promotion of political deliberation.

The Fourth Dialog State Tracking Challenge.

Abstract: Dialog state tracking - the process of updating the dialog state after each interaction with the user - is a key component of most dialog systems. Following a similar scheme to the fourth dialog state tracking challenge, this edition again focused on human-human dialogs, but introduced the task of cross-lingual adaptation of trackers. The challenge received a total of 32 entries from 9 research groups. In addition, several pilot track evaluations were also proposed receiving a total of 16 entries from 4 groups. In both cases, the results show that most of the groups were able to outperform the provided baselines for each task.

Moses: Open Source Toolkit for Statistical Machine Translation

Abstract: We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder, the toolkit also includes a wide variety of tools for training, tuning and applying the system to many translation tasks.

The Nature and Origins of Mass Opinion.

Abstract: Originally published in Contemporary Psychology: APA Review of Books, 1994, Vol 39(2), 225. Reviews the book, The Nature and Origins of Mass Opinion by John Zaller (1992). The author's commendable effort to specify a model of mass opinion formation offers readers an introduction to the prevailing vi

Lexicon-based methods for sentiment analysis

Abstract: We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text's opinion towards its main subject matter. We show that SO-CAL's performance is consistent across domains and in completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability.

Building end-to-end dialogue systems using generative hierarchical neural network models

Abstract: We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. Generative models produce system responses that are autonomously generated word-by-word, opening up the possibility for realistic, flexible interactions. In support of this goal, we extend the recently proposed hierarchical recurrent encoder-decoder neural network to the dialogue domain, and demonstrate that this model is competitive with state-of-the-art neural language models and backoff n-gram models. We investigate the limitations of this and similar approaches, and show how its performance can be improved by bootstrapping the learning from a larger question-answer pair corpus and from pretrained word embeddings.