Articles

This paper proposes a new automatic ma- chine translation evaluation metric: AMBER, which is based on the metric BLEU but incorporates recall, extra penal- ties, and some text processing variants. There is very little linguistic information in AMBER. We evaluate its system-level cor- relation and sentence-level consistency scores with human …...

We present a pilot study on an evaluation method which is able to rank translation out- puts with no reference translation, given only their source sentence. The system employs a statistical classifier trained upon existing hu- man rankings, using several features derived from analysis of both the source and the …...

This paper presents the results of the WMT11 shared tasks, which included a translation task, a system combination task, and a task for machine translation evaluation metrics. We conducted a large-scale manual evaluation of 148 machine translation systems and 41 sys- tem combination entries. We used the rank- ing of …...

Reordering is a major challenge for machine translation between distant languages. Recent work has shown that evaluation metrics that explicitly account for target language word or- der correlate better with human judgments of translation quality. Here we present a simple framework for evaluating word order indepen- dently of lexical choice …...

This paper describes the submission from the National University of Singapore to the WMT 2011 Shared Evaluation Task and the Tunable Metric Task. Our entry is TESLA in three dif- ferent configurations: TESLA-M, TESLA-F, and the new TESLA-B. 1...

The Workshop on Statistical Machine Translation (WMT) has become one of ACL’s flagship workshops, held annually since 2006. In addition to soliciting pa- pers from the research community, WMT also features a shared translation task for evaluating MT systems. This shared task is notable for having manual evaluation as its …...

Due to its convenience and low–cost, short message service (SMS) has been a very popu- lar medium for communication for quite some time. Unfortunately, however, SMS messages are sometimes used in illicit acts, such as com- munication between drug dealers and buyers, extortion, fraud, scam, hoax, false reports of terrorist …...

Detection of child exploitation in Internet chatting is an important issue for the protec- tion of children from prospective online pae- dophiles. This paper investigates the effectiveness of text classifiers to identify Child Exploitation (CE) in chatting. As the chatting occurs among two or more users by typing texts, the …...

There is a rapidly growing body of work in the use of Embodied Conversational Agents (ECA) to convey complex con- textual relationships through verbal and non-verbal communication, in domains ranging from military C2 to e-learning. In these applications the subject matter ex- pert is often naïve to the technical re- …...

This paper presents an experimental study on the interpretation of plural pronoun they in dis- course, and offers an answer to two questions. The first question is whether the anaphoric in- terpretation of they corresponds to that of its antecedent NP(maximal interpretation), or by the “whole” previous sentence (reference in- …...

This paper presents an experimental study on the interpretation of the complement anaphora the others in inter-sentential discourse. aims to offer an answer to the followingIt two empirical questions. First, how comple- ment anaphora denote the “complement set”, a set of referents that includes those referents not denoted by the …...

This paper describes a supervised algorithm for diacritic restoration based on naive Bayes classifiers that act at word- level. Classifications are based on a rich set of features, extracted automatically from training data in the form of diacritically marked text. The method requires no additional resources, which makes it language …...

Native language identification (NLI) is the task of determining the native language of an author writing in a second language. Several pieces of earlier work have found that fea- tures such as function words, part-of-speech n-grams and syntactic structure are helpful in NLI, perhaps representing characteristic er- rors of different …...

A medical publication may or may not present an outcome. When an outcome is present, its polarity may be positive, negative or neu- tral. Information about the polarity of an out- come is a vital one, particularly for practi- tioners who use the outcome information for decision making. We model …...

In a collocation, the choice of one lexical item depends on the choice made for another. This poses a problem for simple approaches to lex- icalisation in natural language generation sys- tems. In the Meaning-Text framework, recur- rent patterns of collocations have been char- acterised by lexical functions, which offer …...

Providing timely and individualised feedback to students in large undergraduate classes is problematic. In this paper we describe our approach to creating a simple, surface-based, domain-independent natural language tutor which uses simple machine learning tech- niques as a step towards resolving this issue. The focus of our efforts was on …...

Web user forums are valuable means for users to resolve specific information needs, both interactively for participants and stati- cally for users who search/browse over histor- ical thread data. However, the complex struc- ture of forum threads can make it difficult for users to extract relevant information. Thread linking structure …...

In this paper we introduce some of the key NLP-related problems related to the practice of Evidence Based Medicine and propose the task of multi-document query-focused sum- marisation as a key approach to solve these problems. We have completed a corpus for the development of such multi-document query- focused summarisation …...

Automatically building domain-specific on- tologies is a highly challenging task as it re- quires extracting domain-specific terms from a corpus and assigning them relevant domain concept labels. In this paper, we focus on the second task: i.e., assigning domain concepts to domain-specific terms. Motivated by pre- vious approaches in related …...

This paper examines the ways in which par- allelism can be used to speed the parsing of dense PCFGs. We focus on two kinds of parallelism here: Symmetric Multi-Processing (SMP) parallelism on shared-memory multi- core CPUs, and Single-Instruction Multiple- Thread (SIMT) parallelism on GPUs. We de- scribe how to achieve …...