A common problem in cognitive modelling is lack of access to accurate broad-coverage models of event-level surprisal.As shown in, e.g., Bicknell et al. (2010), event-level knowledge does affect human expectations for verbal arguments.For example, the model should be able to predict that mechanics are likely to check tires, while journalists are more likely to check typos.Similarly, we would like to predict what locations are likely for playing football or playing flute in order to estimate the surprisal of actually-encountered locations.Furthermore, such a model can be used to provide a probability distribution over fillers for a thematic role which is not mentioned in the text at all.To this end, we train two neural network models (an incremental one and a non-incremental one) on large amounts of automatically rolelabelled text.Our models are probabilistic and can handle several roles at once, which also enables them to learn interactions between different role fillers.Evaluation shows a drastic improvement over current state-of-the-art systems on modelling human thematic fit judgements, and we demonstrate via a sentence similarity task that the system learns highly useful embeddings.

We present the first large-scale English "allwords lexical substitution" corpus.The size of the corpus provides a rich resource for investigations into word meaning.We investigate the nature of lexical substitute sets, comparing them to WordNet synsets.We find them to be consistent with, but more fine-grained than, synsets.We also identify significant differences to results for paraphrase ranking in context reported for the SEMEVAL lexical substitution data.This highlights the influence of corpus construction approaches on evaluation results.

Humans use rich natural language to describe and communicate visual perceptions. In order to provide natural language descriptions for visual content, this paper combines two important ingredients. First, we generate a rich semantic representation of the visual content including e.g. object and activity labels. To predict the semantic representation we learn a CRF to model the relationships between different components of the visual input. And second, we propose to formulate the generation of natural language as a machine translation problem using the semantic representation as source language and the generated sentences as target language. For this we exploit the power of a parallel corpus of videos and textual descriptions and adapt statistical machine translation to translate between our two languages. We evaluate our video descriptions on the TACoS dataset, which contains video snippets aligned with sentence descriptions. Using automatic evaluation and human judgments we show significant improvements over several baseline approaches, motivated by prior work. Our translation approach also shows improvements over related work on an image description task.

Recent work has shown that the integration of visual information into text-based models can substantially improve model predictions, but so far only visual information extracted from static images has been used. In this paper, we consider the problem of grounding sentences describing actions in visual information extracted from videos. We present a general purpose corpus that aligns high quality videos with multiple natural language descriptions of the actions portrayed in the videos, together with an annotation of how similar the action descriptions are to each other. Experimental results demonstrate that a text-based model of similarity between actions improves substantially when combined with visual information from videos depicting the described actions.

We show how to compute readings of ambiguous natural language sentences that are minimal in some way. Formally, we consider the problem of computing, out of a set C of trees and a rewrite system R, those trees in C that cannot be rewritten into a tree in C. We solve the problem for sets of trees that are described by semantic representations typically used in computational linguistics, and a certain class of rewrite systems that we use to approximate entailment, and show how to compute the irreducible trees efficiently by intersecting tree automata. Our algorithm solves the problem of computing weakest readings that has been open for 25 years in computational linguistics.

Abstract In this article, we underpin the intuition that frame semantic information is a useful resource for modelling textual entailment. To this end, we provide a manual frame semantic annotation for the test set used in the second recognizing textual entailment (RTE) challenge – the FrameNet-annotated textual entailment (FATE) corpus – and discuss experiments we conducted on this basis. In particular, our experiments show that the frame semantic lexicon provided by the Berkeley FrameNet project provides surprisingly good coverage for the task at hand. We identify issues of automatic semantic analysis components, as well as insufficient modelling of the information provided by frame semantic analysis as reasons for ambivalent results of current systems based on frame semantics.

We present an efficient algorithm for the redundancy elimination problem: Given an underspecified semantic representation (USR) of a scope ambiguity, compute an USR with fewer mutually equivalent readings. The algorithm operates on underspecified chart representations which are derived from dominance graphs; it can be applied to the USRs computed by large-scale grammars. We evaluate the algorithm on a corpus, and show that it reduces the degree of ambiguity significantly while taking negligible runtime.

We show that a practical translation of MRS descriptions into normal dominance constraints is feasible. We start from a recent theoretical translation and verify its assumptions on the outputs of the English Resource Grammar (ERG) on the Redwoods corpus. The main assumption of the translation---that all relevant underspecified descriptions are nets---is validated for a large majority of cases; all non-nets computed by the ERG seem to be systematically incomplete.

Minimal Recursion Semantics (MRS) is the standard formalism used in large-scale HPSG grammars to model underspecified semantics. We present the first provably efficient algorithm to enumerate the readings of MRS structures, by translating them into normal dominance constraints.

While the generative view of language processing builds bigger units out of smaller ones by means of rewriting steps, the axiomatic view eliminates invalid linguistic structures out of a set of possible structures by means of well formedness principles. We present a generator based on the axiomatic view and argue that when combined with a TAG-like grammar and a flat semantics, this axiomatic view permits avoiding drawbacks known to hold either of top-down or of bottom-up generators.