1,721,030 research outputs found
Treebank for Dialogue: a case study from Roman Tragedy
No full textThis paper presents a case study on dialogues in
dramatic texts, leveraging a treebank enhanced
with annotation of speakers. Information on
characters speaking contributes to investigate
dialogues from various perspectives, including
the study of interaction and linguistic charac-
terisation
The Sequence Notation:Catching Complex Meanings in Simple Graphs
Full text linkCurrent symbolic semantic representations proposed to capture the semantics of human language have served well to give us insight in how meaning is expressed. But they are either too complicated for large-scale annotation tasks or lack expressive power to play a role in inference tasks. What we propose is a meaning representation system that it is interlingual, model-theoretic, and variable-free. It divides the labour involved in representing meaning along three levels: concept, roles, and contexts. As natural languages are expressed as sequences of phonemes or words, the meaning representations that we propose are likewise sequential. However, the resulting meaning representations can also be visualised as directed acyclic graphs
Implicit causality in GPT-2: a case study
No full textThis case study investigates the extent to which a language model (GPT-2) is able to capture native speakers' intuitions about implicit causality in a sentence completion task. Study 1 reproduces earlier results (showing that the model's surprisal values correlate with the implicit causality bias of the verb; Davis and van Schijndel 2021), and then examine the effects of gender and verb frequency on model performance. Study 2 examines the reasoning ability of GPT-2: Is the model able to produce more sensible motivations for why the subject VERBed the object if the verbs have stronger causality biases? For this study we took care to avoid human raters being biased by obscenities and disfluencies generated by the model
The Sequence Notation:Catching Complex Meanings in Simple Graphs
Full text linkCurrent symbolic semantic representations proposed to capture the semantics of human language have served well to give us insight in how meaning is expressed. But they are either too complicated for large-scale annotation tasks or lack expressive power to play a role in inference tasks. What we propose is a meaning representation system that it is interlingual, model-theoretic, and variable-free. It divides the labour involved in representing meaning along three levels: concept, roles, and contexts. As natural languages are expressed as sequences of phonemes or words, the meaning representations that we propose are likewise sequential. However, the resulting meaning representations can also be visualised as directed acyclic graphs
Enthymemes and Topoi in Dialogue
Full text linkIn Enthymemes and Topoi in Dialogue, Ellen Breitholtz presents a novel and precise account of reasoning from an interactional perspective. The account draws on the concepts of enthymemes and topoi, originating in Aristotelian rhetoric and dialectic, and integrates these in a formal dialogue semantic account using TTR, a type theory with records. Argumentation analysis and formal approaches to reasoning often focus the logical validity of arguments on inferences made in discourse from a god’s-eye perspective. In contrast, Breitholtz’s account emphasises the individual perspectives of interlocutors and the function and acceptability of their reasoning in context. This provides an analysis of interactions where interlocutors have access to different topoi and therefore make different inferences. Readership: All interested in the pragmatics-rhetoric interface and in theories of meaning and coherence in dialogue and discourse
The Sequence Notation:Catching Complex Meanings in Simple Graphs
Full text linkCurrent symbolic semantic representations proposed to capture the semantics of human language have served well to give us insight in how meaning is expressed. But they are either too complicated for large-scale annotation tasks or lack expressive power to play a role in inference tasks. What we propose is a meaning representation system that it is interlingual, model-theoretic, and variable-free. It divides the labour involved in representing meaning along three levels: concept, roles, and contexts. As natural languages are expressed as sequences of phonemes or words, the meaning representations that we propose are likewise sequential. However, the resulting meaning representations can also be visualised as directed acyclic graphs
The Sequence Notation:Catching Complex Meanings in Simple Graphs
Full text linkCurrent symbolic semantic representations proposed to capture the semantics of human language have served well to give us insight in how meaning is expressed. But they are either too complicated for large-scale annotation tasks or lack expressive power to play a role in inference tasks. What we propose is a meaning representation system that it is interlingual, model-theoretic, and variable-free. It divides the labour involved in representing meaning along three levels: concept, roles, and contexts. As natural languages are expressed as sequences of phonemes or words, the meaning representations that we propose are likewise sequential. However, the resulting meaning representations can also be visualised as directed acyclic graphs
The Sequence Notation:Catching Complex Meanings in Simple Graphs
Full text linkCurrent symbolic semantic representations proposed to capture the semantics of human language have served well to give us insight in how meaning is expressed. But they are either too complicated for large-scale annotation tasks or lack expressive power to play a role in inference tasks. What we propose is a meaning representation system that it is interlingual, model-theoretic, and variable-free. It divides the labour involved in representing meaning along three levels: concept, roles, and contexts. As natural languages are expressed as sequences of phonemes or words, the meaning representations that we propose are likewise sequential. However, the resulting meaning representations can also be visualised as directed acyclic graphs
Can current NLI systems handle German word order? Investigating language model performance on a new German challenge set of minimal pairs
No full textCompared to English, German word order is freer and therefore poses additional challenges for natural language inference (NLI). We create WOGLI (Word Order in German Language Inference), the first adversarial NLI dataset for German word order that has the following properties: (i) each premise has an entailed and a non-entailed hypothesis; (ii) premise and hypotheses differ only in word order and necessary morphological changes to mark case and number. In particular, each premise and its two hypotheses contain exactly the same lemmata. Our adversarial examples require the model to use morphological markers in order to recognise or reject entailment. We show that current German autoencoding models fine-tuned on translated NLI data can struggle on this challenge set, reflecting the fact that translated NLI datasets will not mirror all necessary language phenomena in the target language. We also examine performance after data augmentation as well as on related word order phenomena derived from WOGLI. Our datasets are publically available at https://github.com/ireinig/wogli
Implicit causality in GPT-2: a case study
No full textThis case study investigates the extent to which a language model (GPT-2) is able to capture native speakers' intuitions about implicit causality in a sentence completion task. Study 1 reproduces earlier results (showing that the model's surprisal values correlate with the implicit causality bias of the verb; Davis and van Schijndel 2021), and then examine the effects of gender and verb frequency on model performance. Study 2 examines the reasoning ability of GPT-2: Is the model able to produce more sensible motivations for why the subject VERBed the object if the verbs have stronger causality biases? For this study we took care to avoid human raters being biased by obscenities and disfluencies generated by the model
- …
