Articles

While recent changes in Machine Trans- lation state-of-the-art brought translation quality a step further, it is regularly ac- knowledged that the standard automatic metrics do not provide enough insights to fully measure the impact of neural models. This paper proposes a new type of evalu- ation focused specifically on the …...

NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization over the rich vocabulary in morpholog- ically rich languages with strong inflec- tional phenomena. …...

Translation into a morphologically rich language requires a large output vocabu- lary to model various morphological phe- nomena, which is a challenge for neu- ral machine translation architectures. To address this issue, the present paper in- vestigates the impact of having two out- put factors with a system able to …...

Word sense disambiguation is necessary in translation because different word senses often have different translations. Neural machine translation models learn differ- ent senses of words as part of an end- to-end translation task, and their capabil- ity to perform word sense disambiguation has so far not been quantified. We ex- …...

Statistical machine translation (SMT) sys- tems use local cues from n-gram trans- lation and language models to select the translation of each source word. Such systems do not explicitly perform word sense disambiguation (WSD), although this would enable them to select transla- tions depending on the hypothesized sense of each …...

For efficiency considerations, state-of-the- art neural machine translation (NMT) re- quires the vocabulary to be restricted to a limited-size set of several thousand sym- bols. This is highly problematic when translating into inflected or compounding languages. A typical remedy is the use of subword units, where words are seg- mented …...

AbstractThis paper explores extending shallow semantic parsing beyond lexical-unit triggers, using causal relations as a test case. Semantic parsing becomes difficult in the face of the wide variety of linguistic realizations that causation can take on. We therefore base our approach on the concept of constructions from the linguistic paradigm …...

AbstractPast work in relation extraction has focused on binary relations in single sentences. Recent NLP inroads in high-value domains have sparked interest in the more general setting of extracting n-ary relations that span multiple sentences. In this paper, we explore a general relation extraction framework based on graph long short-term …...

AbstractIn neural machine translation (NMT), generation of a target word depends on both source and target contexts. We find that source contexts have a direct impact on the adequacy of a translation while target contexts affect the fluency. Intuitively, generation of a content word should rely more on the source …...

AbstractWe present a probabilistic model of phonotactics, the set of well-formed phoneme sequences in a language. Unlike most computational models of phonotactics (Hayes and Wilson, 2008; Goldsmith and Riggle, 2012), we take a fully generative approach, modeling a process where forms are built up out of subparts by phonologically-informed structure …...

AbstractDecoding of phrase-based translation models in the general case is known to be NP-complete, by a reduction from the traveling salesman problem (Knight, 1999). In practice, phrase-based systems often impose a hard distortion limit that limits the movement of phrases during translation. However, the impact on complexity after imposing such …...

AbstractTransition-based models can be fast and accurate for constituent parsing. Compared with chart-based models, they leverage richer features by extracting history information from a parser stack, which consists of a sequence of non-local constituents. On the other hand, during incremental parsing, constituent information on the right hand side of the …...

AbstractRecent research in psycholinguistics has provided increasing evidence that humans predict upcoming content. Prediction also affects perception and might be a key to robustness in human language processing. In this paper, we investigate the factors that affect human prediction by building a computational model that can predict upcoming discourse referents …...

AbstractImportant advances have recently been made using computational semantic models to decode brain activity patterns associated with concepts; however, this work has almost exclusively focused on concrete nouns. How well these models extend to decoding abstract nouns is largely unknown. We address this question by applying state-of-the-art computational models to …...

AbstractProbabilistic topic models are important tools for indexing, summarizing, and analyzing large document collections by their themes. However, promoting end-user understanding of topics remains an open research problem. We compare labels generated by users given four topic visualization techniques—word lists, word lists with bars, word clouds, and network graphs—against each …...

In this paper we describe a comparison of two annotation schemes for de- pendency parsing of North Sámi, a Finno-Ugric language spoken in the north of Scandinavia and Finland. The two annotation schemes are the Giellatekno (GT) scheme which has been used in research and applications for the Sámi languages …...

In this paper, we offer an overview of language technology tools and resources (being) developed for an endangered minority language, Mansi. We pay special attention to lexical resources and morphological analyzers. Online dictionaries, morphological analyzers and a corpus are already available (or will be made avail- able soon) for the …...

This paper presents different experiments aiming at automatically extracting lexical information from corpora. We first describe a simple experiment on the nature of direct objects in Finnish (partitive vs total objects) so as to check if data automatically extracted from corpora support traditional studies in the field. Which are the …...

For most of the Uralic languages, there is a lack of systematically collected, consequently transcribed and morphologically annotated text corpora. This pa- per sums up the steps, the preliminary results and the future directions of build- ing a linguistic corpus of some Uralic languages, namely Tundra Nenets, Udmurt, Synya Khanty, …...

The paper describes work-in-progress by the Pite Saami, Kola Saami and Izhva Komi language documentation projects, all of which use similar data and techni- cal frameworks and are carried out in Freiburg and in collaboration with Ham- burg, Syktyvkar, Tromsø and Uppsala. Our projects work in the endangered lan- guage …...