Annemarie Friedrich

Coherent Multi-sentence Video Description with Variable Level of Detail

Humans can easily describe what they see in a coherent way and at varying level of detail. However, existing approaches for automatic video description focus on generating only single sentences and are not able to vary the descriptions’ level of detail. In this paper, we address both of these limitations: for a variable level of detail we produce coherent multi-sentence descriptions of complex videos. To understand the difference between detailed and short descriptions, we collect and analyze a video description corpus of three levels of detail. We follow a two-step approach where we first learn to predict a semantic representation (SR) from video and then generate natural language descriptions from it. For our multi-sentence descriptions we model across-sentence consistency at the level of the SR by enforcing a consistent topic. Human judges rate our descriptions as more readable, correct, and relevant than related work.

Automatic prediction of aspectual class of verbs in context

This paper describes a new approach to predicting the aspectual class of verbs in context, i.e., whether a verb is used in a stative or dynamic sense. We identify two challenging cases of this problem: when the verb is unseen in training data, and when the verb is ambiguous for aspectual class. A semi-supervised approach using linguistically-motivated features and a novel set of distributional features based on representative verb types allows us to predict classes accurately, even for unseen verbs. Many frequent verbs can be either stative or dynamic in different contexts, which has not been modeled by previous work; we use contextual features to resolve this ambiguity. In addition, we introduce two new datasets of clauses marked for aspectual class.

Situation Entity Annotation

This paper presents an annotation scheme for a new semantic annotation task with relevance for analysis and computation at both the clause level and the discourse level. More specifically, we label the finite clauses of texts with the type of situation entity (e.g., eventualities, statements about kinds, or statements of belief) they introduce to the discourse, following and extending work by Smith (2003). We take a feature-driven approach to annotation, with the result that each clause is also annotated with fundamental aspectual class, whether the main NP referent is specific or generic, and whether the situation evoked is episodic or habitual. This annotation is performed (so far) on three sections of the MASC corpus, with each clause labeled by at least two annotators. In this paper we present the annotation scheme, statistics of the corpus in its current version, and analyses of both inter-annotator agreement and intra-annotator consistency.

Annotating genericity: a survey, a scheme, and a corpus

Generics are linguistic expressions that make statements about or refer to kinds, or that report regularities of events. Non-generic expressions make statements about particular individuals or specific episodes. Generics are treated extensively in semantic theory (Krifka et al., 1995). In practice, it is often hard to decide whether a referring expression is generic or non-generic, and to date there is no data set which is both large and satisfactorily annotated. Such a data set would be valuable for creating automatic systems for identifying generic expressions, in turn facilitating knowledge extraction from natural language text. In this paper we provide the next steps for such an annotation endeavor. Our contributions are: (1) we survey the most important previous projects annotating genericity, focusing on resources for English; (2) with a new agreement study we identify problems in the annotation scheme of the largest currentlyavailable resource (ACE-2005); and (3) we introduce a linguistically-motivated annotation scheme for marking both clauses and their subjects with regard to their genericity. (4) We present a corpus of MASC (Ide et al., 2010) and Wikipedia texts annotated according to our scheme, achieving substantial agreement.

Situation entity types: automatic classification of clause-level aspect.

This paper describes the first robust approach to automatically labeling clauses with their situation entity type (Smith, 2003), capturing aspectual phenomena at the clause level which are relevant for interpreting both semantics at the clause level and discourse structure. Previous work on this task used a small data set from a limited domain, and relied mainly on words as features, an approach which is impractical in larger settings. We provide a new corpus of texts from 13 genres (40,000 clauses) annotated with situation entity types. We show that our sequence labeling approach using distributional information in the form of Brown clusters, as well as syntactic-semantic features targeted to the task, is robust across genres, reaching accuracies of up to 76%.

Discourse-sensitive Automatic Identification of Generic Expressions

This paper describes a novel sequence labeling method for identifying generic expressions, which refer to kinds or arbitrary members of a class, in discourse context. The automatic recognition of such expressions is important for any natural language processing task that requires text understanding. Prior work has focused on identifying generic noun phrases; we present a new corpus in which not only subjects but also clauses are annotated for genericity according to an annotation scheme motivated by semantic theory. Our contextaware approach for automatically identifying generic expressions uses conditional random fields and outperforms previous work based on local decisions when evaluated on this corpus and on related data sets (ACE-2 and ACE-2005).

Linking discourse modes and situation entity types in a cross-linguistic corpus study

The main contribution of this paper is a cross-linguistic empirical analysis of two interacting levels of linguistic analysis of written text: situation entity (SE) types, the semantic types of situations evoked by clauses of text, and discourse modes (DMs), a characterization of passages at the sub-document level. We adapt an existing annotation scheme for SEs in English to be used for German data, with a detailed discussion of the most important differences. We create the first parallel corpus annotated for SEs, and the first DM-annotated corpus. We find that: (a) the adapted scheme is supported by evidence from a large-scale experimental study; (b) SEs mainly correspond to each other in parallel text, and a large part of the mismatches are systematic; (c) the DM annotation task can be performed intuitively with reasonable agreement; and (d) the annotated DMs show the predicted differences in the distributions of SE types.

Semantically Enriched Models for Modal Sense Classification

Modal verbs have different interpretations depending on their context. Previous approaches to modal sense classification achieve relatively high performance using shallow lexical and syntactic features. In this work we uncover the difficulty of particular modal sense distinctions by eliminating both distributional bias and sparsity of existing small-scale annotated corpora used in prior work. We build a semantically enriched model for modal sense classification by novelly applying features that relate to lexical, proposition-level, and discourse-level semantic factors. Besides improved classification performance, especially for difficult sense distinctions, closer examination of interpretable feature sets allows us to obtain a better understanding of relevant semantic and contextual factors in modal sense classification.

Annotating tense, mood and voice for English, French and German

We present the first open-source tool for annotating morphosyntactic tense, mood and voice for English, French and German verbal complexes. The annotation is based on a set of language-specific rul ...

Automatic recognition of habituals: a three-way classification of clausal aspect

This paper provides the first fully automatic approach for classifying clauses with respect to their aspectual properties as habitual, episodic or static. We bring together two strands of previous work, which address only the related tasks of the episodic-habitual and stative-dynamic distinctions, respectively. Our method combines different sources of information found to be useful for these tasks. We are the first to exhaustively classify all clauses of a text, achieving up to 80% accuracy (baseline 58%) for the three-way classification task, and up to 85% accuracy for related subtasks (baselines 50% and 60%), outperforming previous work. In addition, we provide a new large corpus of Wikipedia texts labeled according to our linguistically motivated guidelines.