Articles

In this paper, we report on an experiment carried out in the context of a translation company. Ten translators, with diverse degrees of experience in translation and machine translation post- editing (MTPE), were assigned the same task, involving translation from scratch, fuzzy-match post-editing, and MTPE. We evaluate the MT output …...

Joint models have recently shown to improve the state-of-the-art in machine translation (MT). We apply EM-based mixture modeling and data selection techniques using two joint models, namely the Operation Sequence Model or OSM — an ngram-based translation and reordering model, and the Neural Network Joint Model or NNJM — a …...

The lack of parallel data for many language pairs is an important challenge to statistical ma- chine translation (SMT). One common solution is to pivot through a third language for which there exist parallel corpora with the source and target languages. Although pivoting is a ro- bust technique, it introduces …...

We report on experiments to test the effectiveness of controlled language (CL) rules on texts from Japanese municipal websites. We compiled a set of rules by trial and error, systematically rewriting Japanese source texts and analysing the machine translation (MT) outputs. We then employed native English speakers with little knowledge …...

This paper proposes an extension of METEOR, a well-known MT evaluation metric, for multiple target languages using an in-house lexical resource called DBnary (an extraction from Wiktionary provided to the community as a Multilingual Lexical Linked Open Data). Today, the use of the synonymy module of METEOR is only exploited …...

In this paper we present a method of detecting zero pronouns in Japanese clauses and identifying their antecedents using aligned sentence pairs from a Japanese-English bilingual corpus and open resource tools. We use syntactic and semantic structures and the alignment of words and phrases in the sentence pairs to automatically …...

Typical MT training involves several stages, including word alignment, rule extraction, trans- lation model estimation, and parameter tuning. In this paper, different from the traditional pipeline, we investigate the possibility of end-to-end MT training, and propose a framework which combines rule induction and parameter tuning in one single module. Preliminary …...

We introduce a novel method for bilingual phrase representation with Recurrent Neural Net- works (RNNs), which transforms a sequence of word feature vectors into a fixed-length phrase vector across two languages. Our method measures the difference between the vectors of source- and target-side phrases, and can be used to predict …...

Following the idea of using distributed semantic representations to facilitate the computation of semantic similarity between translation equivalents, we propose a novel framework to learn bilingual distributed phrase representations for machine translation. We first induce vector representations for words in the source and target language respectively, in their own semantic …...

This paper proposes a well-formed depen- dency to string translation model with BTG grammar. By enabling the usage of well- formed sub-structures and allowing flexible reordering of them, our approach is effective to relieve the problems of parsing error and flatness in dependency structure. To utilize the well-formed dependency rules …...

1 Difangzhi (地方志) is a large collection of local gazetteers complied by local govern- ments of China, and the documents provide invaluable information about the host locali- ty. This paper reports the current status of using natural language processing and text mining methods to identify biographical in- formation of government …...

Relation classification is an important se- mantic processing, which has achieved great attention in recent years. The main challenge is the fact that important infor- mation can appear at any position in the sentence. Therefore, we propose bidirec- tional long short-term memory networks (BLSTM) to model the sentence with complete, …...

We propose a method for implicit discourse relation recognition using a recursive neural network (RNN). Many previous studies have used the word-pair feature to compare the meaning of two sentences for implicit dis- course relation recognition. Our proposed method differs in that we use various-sized sentence expression units and compare …...

In this paper, we conducted semantic trans- parency rating experiments using both the traditional laboratory-based method and the crowdsourcing-based method. Then we com- pared the rating data obtained from these two experiments. We observed very strong cor- relation coefficients for both overall seman- tic transparency rating data and constituent se- …...

Semantic text similarity (STS) is an essential problem in many Natural Language Pro- cessing tasks, which has drawn a considerable amount of attention by research community in recent years. In this paper, our work focused on computing semantic similarity between texts of sentence length. We employed a Sup- port Vector …...

This paper proposes a surrounding word sense model (SWSM) that uses the distri- bution of word senses that appear near am- biguous words for unsupervised all-words word sense disambiguation in Japanese. Although it was inspired by the topic model, ambiguous Japanese words tend to have similar topics since coarse semantic …...

Detecting language divergences and predict- ing possible sub-translations is one of the most essential issues in machine translation. Since the existence of translation divergences, it is impractical to straightforward translate from source sentence into target sentence while keeping the high degree of accuracy and with- out additional information. In this …...

We present in this paper PADIC, a Parallel Arabic DIalect Corpus we built from scratch, then we conducted experiments on cross- dialect Arabic machine translation. PADIC is composed of dialects from both the Maghreb and the Middle-East. Each dialect has been aligned with Modern Standard Arabic (MSA). Three dialects from …...

Entity linking is an indispensable oper- ation of populating knowledge reposito- ries for information extraction. It stud- ies on aligning a textual entity mention to its corresponding disambiguated entry in a knowledge repository. In this paper, we propose a new paradigm named dis- tantly supervised entity linking (DSEL), in the …...

This paper is a brief review of the research on language variation using corpus data and statistical modeling methods. The variation phenomena covered in this review include phonetic variation (in spontaneous speech) and syntactic variation, with a focus on studies of English and Chinese. The goal of this paper is …...