Articles

AbstractIn recent years, several end-to-end online translation systems have been proposed to successfully incorporate human post-editing feedback in the translation workflow. The performance of these systems in a multi-domain translation environment (involving different text genres, post-editing styles, machine translation systems) within the automatic post-editing (APE) task has not been thoroughly …...

A difficult task when generating text from knowledge bases (KB) consists in finding appropriate lexicalisations for KB sym- bols. We present an approach for lexicalis- ing knowledge base relations and apply it to DBPedia data. Our model learns low- dimensional embeddings of words and RDF resources and uses these represen- …...

Users combine attributes and types to describe and classify entities into cate- gories. These categories are fundamen- tal for organising knowledge in a decen- tralised way acting as tags and predi- cates. When searching for entities, ca- tegories frequently describes the search query. Considering that users do not know in …...

We study the automatic detection of sug- gestion expressing text among the opin- ionated text. The examples of such sug- gestions in online reviews would be, cus- tomer suggestions about improvement in a commercial entity, and advice to the fel- low customers. We present a qualitative and quantitative analysis of …...

The linguistic experiences of a person are an important part of their individuality. In this paper, we show that people can be modelled as vectors in a semantic space, using their personal interaction with spe- cific language data. We also demonstrate that these vectors can be taken as repre- sentative …...

Givenness (Schwarzschild, 1999) is one of the central notions in the formal pragmatic literature discussing the organization of dis- course. In this paper, we explore where distributional semantics can help address the gap between the linguistic insights into the formal pragmatic notion of Givenness and its implementation in computational linguistics. …...

One may express favor (or disfavor) to- wards a target by using positive or neg- ative language. Here for the first time we present a dataset of tweets annotated for whether the tweeter is in favor of or against pre-chosen targets, as well as for sentiment. These targets may or …...

In this paper, we explore the role of con- stituent properties in English and Ger- man noun-noun compounds (corpus fre- quencies of the compounds and their con- stituents; productivity and ambiguity of the constituents; and semantic relations between the constituents), when predict- ing the degrees of compositionality of the compounds …...

We introduce positive-only projection (PoP), a new algorithm for constructing semantic spaces and word embeddings. The PoP method employs random projec- tions. Hence, it is highly scalable and com- putationally efficient. In contrast to pre- vious methods that use random projec- tion matrices R with the expected value of 0 …...

Learning embeddings of words and knowledge base elements is a promising approach for open domain question answering. Based on the remark that relations and entities are distinct object types lying in the same embedding space, we analyze the benefit of adding a regularizer favoring the embeddings of entities to be …...

Segmenting text into semantically coher- ent fragments improves readability of text and facilitates tasks like text summariza- tion and passage retrieval. In this pa- per, we present a novel unsupervised al- gorithm for linear text segmentation (TS) that exploits word embeddings and a mea- sure of semantic relatedness of short …...

In this paper, we propose methods to take into account the disagreement between crowd annotators as well as their skills for weighting instances in learning algo- rithms. The latter can thus better deal with noise in the annotation and produce higher accuracy. We created two passage rerank- ing datasets: one …...

We describe the implementation of a Word Sense Disambiguation (WSD) tool in a Dutch Text-to-Pictograph translation sys- tem, which converts textual messages into sequences of pictographic images. The system is used in an online platform for Augmentative and Alternative Communi- cation (AAC). In the original translation process, the appropriate sense …...

We investigate style accommodation in online discussions, in particular its inter- play with content agreement and disagree- ment. Using a new model for measuring style accommodation, we find that speak- ers coordinate on style more noticeably if they disagree than if they agree, especially if they want to establish rapport …...

In this paper, we aim to close the gap from extensive, human-built semantic re- sources and corpus-driven unsupervised models. The particular resource explored here is VerbNet, whose organizing princi- ple is that semantics and syntax are linked. To capture patterns of usage that can aug- ment knowledge resources like VerbNet, …...

Recognizing lexical inferences between pairs of terms is a common task in NLP applications, which should typically be performed within a given context. Such context-sensitive inferences have to con- sider both term meaning in context as well as the fine-grained relation hold- ing between the terms. Hence, to de- velop …...

Distributional semantic models can pre- dict many linguistic phenomena, including word similarity, lexical ambiguity, and se- mantic priming, or even to pass TOEFL synonymy and analogy tests (Landauer and Dumais, 1997; Griffiths et al., 2007; Turney and Pantel, 2010). But what does it take to create a competitive distributional model? …...

Recent models in distributional seman- tics consider derivational patterns (e.g., use → use + f ul) as the result of a compositional process, where base term and affix are combined. We exploit such models for German particle verbs (PVs), and focus on the task of learning a mapping function between …...

Conventional word sense induction (WSI) methods usually represent each instance with discrete linguistic features or co- occurrence features, and train a model for each polysemous word individually. In this work, we propose to learn sense embeddings for the WSI task. In the training stage, our method induces sev- eral sense …...

In a complex sentence comprised of one or more subclauses, the overt or hidden atti- tudes between the various entities depend on the factuality projection of the verbs, their polar effects, and the modality and affirmative status (negated or not) of the clauses. If factuality is given, some refer- ents …...