7 When do discourse markers affect computational sentence understanding?
-
Ruiqi Li
Abstract
The capabilities and use cases of automatic natural language processing (NLP) have grown significantly over the last few years. While much work has been devoted to understanding how humans deal with discourse connectives, this phenomenon is understudied in computational systems. Therefore, it is important to put NLP models under the microscope and examine whether they can adequately comprehend, process, and reason within the complexity of natural language. In this chapter, we introduce the main mechanisms behind automatic sentence processing systems step by step and then focus on evaluating discourse connective processing. We assess nine popular systems in their ability to understand English discourse connectives and analyze how context and language understanding tasks affect their connective comprehension. The results show that NLP systems do not process all discourse connectives equally well and that the computational processing complexity of different connective kinds is not always consistently in line with the presumed complexity order found in human processing. In addition, while humans are more inclined to be influenced during the reading procedure but not necessarily in the final comprehension performance, discourse connectives have a significant impact on the final accuracy of NLP systems. The richer knowledge of connectives a system learns, the more negative effect inappropriate connectives have on it. This suggests that the correct explicitation of discourse connectives is important for computational natural language processing.
Abstract
The capabilities and use cases of automatic natural language processing (NLP) have grown significantly over the last few years. While much work has been devoted to understanding how humans deal with discourse connectives, this phenomenon is understudied in computational systems. Therefore, it is important to put NLP models under the microscope and examine whether they can adequately comprehend, process, and reason within the complexity of natural language. In this chapter, we introduce the main mechanisms behind automatic sentence processing systems step by step and then focus on evaluating discourse connective processing. We assess nine popular systems in their ability to understand English discourse connectives and analyze how context and language understanding tasks affect their connective comprehension. The results show that NLP systems do not process all discourse connectives equally well and that the computational processing complexity of different connective kinds is not always consistently in line with the presumed complexity order found in human processing. In addition, while humans are more inclined to be influenced during the reading procedure but not necessarily in the final comprehension performance, discourse connectives have a significant impact on the final accuracy of NLP systems. The richer knowledge of connectives a system learns, the more negative effect inappropriate connectives have on it. This suggests that the correct explicitation of discourse connectives is important for computational natural language processing.
Kapitel in diesem Buch
- Frontmatter I
- Contents V
- 1 Discourse markers in interaction: Introduction 1
- 2 Principles of Discourse Marking: An experimental approach of general and contrastive perspectives 17
- 3 New perspectives on car and parce que: Is it about subjectivity, reasoning or speakers? 45
- 4 Individual differences in the ability to master connectives: The importance of exposure to print 69
- 5 Do non-native readers rely on connectives? The processing of coherence relations in L2 89
- 6 How egocentric is discourse marker use? Investigating the impact of speaker orientation and cognitive load on discourse marker production 121
- 7 When do discourse markers affect computational sentence understanding? 159
- 8 Discourse markers and dialogue act annotation for computational dialogue systems 191
- 9 Translating discourse markers: Implicitation and explicitation strategies 215
- 10 Processing polyfunctional discourse markers: Making sense of Hebrew harey 247
- Index 277
Kapitel in diesem Buch
- Frontmatter I
- Contents V
- 1 Discourse markers in interaction: Introduction 1
- 2 Principles of Discourse Marking: An experimental approach of general and contrastive perspectives 17
- 3 New perspectives on car and parce que: Is it about subjectivity, reasoning or speakers? 45
- 4 Individual differences in the ability to master connectives: The importance of exposure to print 69
- 5 Do non-native readers rely on connectives? The processing of coherence relations in L2 89
- 6 How egocentric is discourse marker use? Investigating the impact of speaker orientation and cognitive load on discourse marker production 121
- 7 When do discourse markers affect computational sentence understanding? 159
- 8 Discourse markers and dialogue act annotation for computational dialogue systems 191
- 9 Translating discourse markers: Implicitation and explicitation strategies 215
- 10 Processing polyfunctional discourse markers: Making sense of Hebrew harey 247
- Index 277
