Niloofar montazeri | University of Southern California (original) (raw)

Uploads

Papers by Niloofar montazeri

2022 IEEE 16th International Conference on Semantic Computing (ICSC)

Most of the prior work on goal-oriented dialog systems has concentrated on developing systems tha... more Most of the prior work on goal-oriented dialog systems has concentrated on developing systems that heavily rely on the relevant domain APIs to generate a response. However, in the real world, users frequently make such requests that the provided APIs cannot handle, we call them "off-script" queries. Ideally, existing information retrieval approaches could have leveraged relevant enterprise's unstructured data sources to retrieve the appropriate information to synthesize responses for such queries. But, in multi-turn dialogs, these queries oftentimes are not self-contained, rendering most of the existing information retrieval methods ineffective, and the dialog systems end up responding "sorry I don't know this". That is, off-script queries may mention entities from the previous dialog turns (often expressed through pronouns) or do not mention the referred entities at all. These two problems are known as coreference resolution and ellipsis, respectively; extensively studied research problems in the supervised settings. In this paper, we first build a dataset of off-script and contextual user queries for goaloriented dialog systems. Then, we propose a zero-label approach to rewrite the contextual query as a self-contained one by leveraging the dialog's state. We propose two parallel coreference and ellipsis resolution pipelines to synthesize candidate queries, rank and select the candidates based on the pre-trained language model GPT-2, and refine the selected self-contained query with the pre-trained BERT. We show that our approach leads to higher quality expanded questions compared to state-of-the-art supervised methods, on our dataset and existing datasets. The key advantage of our novel zero-label approach is that it requires no labeled training data and can be applied to any domain seamlessly, in contrast to previous work that requires labeled training data for each new domain.

Words describe the world, so if we are going to draw the appropriate inferences in understanding ... more Words describe the world, so if we are going to draw the appropriate inferences in understanding a text, we must have a prior explication of how we view the world (world knowledge) and how words and phrases map to this view (lexical semantics knowledge). ❧ Existing world knowledge and lexical semantics knowledge resources are not particularly suitable for deep reasoning, either due to lack of connection between their elements or due to their simple knowledge representation method (binary relations between natural language phrases). ❧ To enable deep understanding and reasoning over natural language, (Hobbs 2008) has proposed the idea of ""Deep Lexical Semantics"". In Deep Lexical Semantics, principal and abstract domains of commonsense knowledge are encoded into ""core theories"" and words are linked to these theories through axioms that use predicates from these theories. This research is concerned with the second task: Axiomatizing words in t...

We present a method for finding (STATE, EVENT) pairs where EVENT can change STATE. For example, t... more We present a method for finding (STATE, EVENT) pairs where EVENT can change STATE. For example, the event “realize” can put an end to the states “be unaware”, “be confused”, and “be happy”; while it can rarely affect “being hungry”. We extract these pairs from a large corpus using a fixed set of syntactic dependency patterns. We then apply a supervised Machine Learning algorithm to clean the results using syntactic and collocational features, achieving a precision of 78% and a recall of 90%. We observe 3 different relations between states and events that change them and present a method for using Mechanical Turk to differentiate between these relations

In an enterprise called "deep lexical semantics", we develop various core theories of f... more In an enterprise called "deep lexical semantics", we develop various core theories of fundamental commonsense phenomena and define English word senses by means of axioms using predicates explicated in these theories. This enables deep inferences that require commonsense knowledge about how the world functions. There are difficulties in our approach to manually axiomatize words and commonsense knowledge. First, developing axioms is done by experts and this means the process is slow and expensive. Second, it is hard, if possible at all, to predict in advance all the kinds of axioms that should be encoded in core theories. In this paper we present a method for harvesting from free-form text on the web, simple axioms for change-of-state verbs which is a combination of textmining and manual filtering. Focusing on two change-ofstate verbs, ―break‖ and ―cut‖, we show how the harvested axioms can help in addressing the above problems.

BACKGROUND An increasing number of doctor reviews are being generated by patients on the internet... more BACKGROUND An increasing number of doctor reviews are being generated by patients on the internet. These reviews address a diverse set of topics (features), including wait time, office staff, doctor’s skills, and bedside manners. Most previous work on automatic analysis of Web-based customer reviews assumes that (1) product features are described unambiguously by a small number of keywords, for example, battery for phones and (2) the opinion for each feature has a positive or negative sentiment. However, in the domain of doctor reviews, this setting is too restrictive: a feature such as visit duration for doctor reviews may be expressed in many ways and does not necessarily have a positive or negative sentiment. OBJECTIVE This study aimed to adapt existing and propose novel text classification methods on the domain of doctor reviews. These methods are evaluated on their accuracy to classify a diverse set of doctor review features. METHODS We first manually examined a large number of...

We describe the methodology for constructing axioms defining event-related words, anchored in cor... more We describe the methodology for constructing axioms defining event-related words, anchored in core theories of change of state and causality. We first derive from WordNet senses a smaller set of abstract, general "supersenses". We encode axioms for these, and we test them on textual entailment pairs. We look at two specific examples in detail to illustrate both the power of the method and the holes in the knowledge base that it exposes. Then we address the problem of holes more systematically, asking, for example, what kinds of "pairwise interactions" are possible for core theory predicates like change and cause. 1

Proceedings of the Second Workshop on Metaphor in NLP, 2014

This paper presents a metaphor interpretation pipeline based on abductive inference. In this fram... more This paper presents a metaphor interpretation pipeline based on abductive inference. In this framework following (Hobbs, 1992) metaphor interpretation is modelled as a part of the general discourse processing problem, such that the overall discourse coherence is supported. We present an experimental evaluation of the proposed approach using linguistic data in English and Russian.

Studies in Linguistics and Philosophy, 2013

Text, Speech and Language Technology, 2014

This paper presents a discourse processing framework based on weighted abduction. We elaborate on... more This paper presents a discourse processing framework based on weighted abduction. We elaborate on ideas described in Hobbs et al. (1993) and implement the abductive inference procedure in a system called Mini-TACITUS. Particular attention is paid to constructing a large and reliable knowledge base for supporting inferences. For this purpose we exploit such lexical-semantic resources as WordNet and FrameNet. We test the proposed procedure and the obtained knowledge base on the Recognizing Textual Entailment task using the data sets from the RTE-2 challenge for evaluation. In addition, we provide an evaluation of the semantic role labeling produced by the system taking the Frame-Annotated Corpus for Textual Entailment as a gold standard.

In this paper, with the goal of using Viterbi algorithm as a quick Top-down parsing procedure, a ... more In this paper, with the goal of using Viterbi algorithm as a quick Top-down parsing procedure, a new probabilistic model called “Rule Bi-gram” is introduced. By extending rule bi-gram model, we have implemented a new parsing algorithm (VPA) based on the Viterbi algorithm. Our experiments show that although in applications in which an exact parse of the input sentence is required, this method may not be appropriate, in applications where speed is a crucial criterion (such as real-time speech recognition), the new algorithm performs very efficient and robust.

2022 IEEE 16th International Conference on Semantic Computing (ICSC)

Most of the prior work on goal-oriented dialog systems has concentrated on developing systems tha... more Most of the prior work on goal-oriented dialog systems has concentrated on developing systems that heavily rely on the relevant domain APIs to generate a response. However, in the real world, users frequently make such requests that the provided APIs cannot handle, we call them "off-script" queries. Ideally, existing information retrieval approaches could have leveraged relevant enterprise's unstructured data sources to retrieve the appropriate information to synthesize responses for such queries. But, in multi-turn dialogs, these queries oftentimes are not self-contained, rendering most of the existing information retrieval methods ineffective, and the dialog systems end up responding "sorry I don't know this". That is, off-script queries may mention entities from the previous dialog turns (often expressed through pronouns) or do not mention the referred entities at all. These two problems are known as coreference resolution and ellipsis, respectively; extensively studied research problems in the supervised settings. In this paper, we first build a dataset of off-script and contextual user queries for goaloriented dialog systems. Then, we propose a zero-label approach to rewrite the contextual query as a self-contained one by leveraging the dialog's state. We propose two parallel coreference and ellipsis resolution pipelines to synthesize candidate queries, rank and select the candidates based on the pre-trained language model GPT-2, and refine the selected self-contained query with the pre-trained BERT. We show that our approach leads to higher quality expanded questions compared to state-of-the-art supervised methods, on our dataset and existing datasets. The key advantage of our novel zero-label approach is that it requires no labeled training data and can be applied to any domain seamlessly, in contrast to previous work that requires labeled training data for each new domain.

Words describe the world, so if we are going to draw the appropriate inferences in understanding ... more Words describe the world, so if we are going to draw the appropriate inferences in understanding a text, we must have a prior explication of how we view the world (world knowledge) and how words and phrases map to this view (lexical semantics knowledge). ❧ Existing world knowledge and lexical semantics knowledge resources are not particularly suitable for deep reasoning, either due to lack of connection between their elements or due to their simple knowledge representation method (binary relations between natural language phrases). ❧ To enable deep understanding and reasoning over natural language, (Hobbs 2008) has proposed the idea of ""Deep Lexical Semantics"". In Deep Lexical Semantics, principal and abstract domains of commonsense knowledge are encoded into ""core theories"" and words are linked to these theories through axioms that use predicates from these theories. This research is concerned with the second task: Axiomatizing words in t...

We present a method for finding (STATE, EVENT) pairs where EVENT can change STATE. For example, t... more We present a method for finding (STATE, EVENT) pairs where EVENT can change STATE. For example, the event “realize” can put an end to the states “be unaware”, “be confused”, and “be happy”; while it can rarely affect “being hungry”. We extract these pairs from a large corpus using a fixed set of syntactic dependency patterns. We then apply a supervised Machine Learning algorithm to clean the results using syntactic and collocational features, achieving a precision of 78% and a recall of 90%. We observe 3 different relations between states and events that change them and present a method for using Mechanical Turk to differentiate between these relations

In an enterprise called "deep lexical semantics", we develop various core theories of f... more In an enterprise called "deep lexical semantics", we develop various core theories of fundamental commonsense phenomena and define English word senses by means of axioms using predicates explicated in these theories. This enables deep inferences that require commonsense knowledge about how the world functions. There are difficulties in our approach to manually axiomatize words and commonsense knowledge. First, developing axioms is done by experts and this means the process is slow and expensive. Second, it is hard, if possible at all, to predict in advance all the kinds of axioms that should be encoded in core theories. In this paper we present a method for harvesting from free-form text on the web, simple axioms for change-of-state verbs which is a combination of textmining and manual filtering. Focusing on two change-ofstate verbs, ―break‖ and ―cut‖, we show how the harvested axioms can help in addressing the above problems.

BACKGROUND An increasing number of doctor reviews are being generated by patients on the internet... more BACKGROUND An increasing number of doctor reviews are being generated by patients on the internet. These reviews address a diverse set of topics (features), including wait time, office staff, doctor’s skills, and bedside manners. Most previous work on automatic analysis of Web-based customer reviews assumes that (1) product features are described unambiguously by a small number of keywords, for example, battery for phones and (2) the opinion for each feature has a positive or negative sentiment. However, in the domain of doctor reviews, this setting is too restrictive: a feature such as visit duration for doctor reviews may be expressed in many ways and does not necessarily have a positive or negative sentiment. OBJECTIVE This study aimed to adapt existing and propose novel text classification methods on the domain of doctor reviews. These methods are evaluated on their accuracy to classify a diverse set of doctor review features. METHODS We first manually examined a large number of...

We describe the methodology for constructing axioms defining event-related words, anchored in cor... more We describe the methodology for constructing axioms defining event-related words, anchored in core theories of change of state and causality. We first derive from WordNet senses a smaller set of abstract, general "supersenses". We encode axioms for these, and we test them on textual entailment pairs. We look at two specific examples in detail to illustrate both the power of the method and the holes in the knowledge base that it exposes. Then we address the problem of holes more systematically, asking, for example, what kinds of "pairwise interactions" are possible for core theory predicates like change and cause. 1

Proceedings of the Second Workshop on Metaphor in NLP, 2014

This paper presents a metaphor interpretation pipeline based on abductive inference. In this fram... more This paper presents a metaphor interpretation pipeline based on abductive inference. In this framework following (Hobbs, 1992) metaphor interpretation is modelled as a part of the general discourse processing problem, such that the overall discourse coherence is supported. We present an experimental evaluation of the proposed approach using linguistic data in English and Russian.

Studies in Linguistics and Philosophy, 2013

Text, Speech and Language Technology, 2014

This paper presents a discourse processing framework based on weighted abduction. We elaborate on... more This paper presents a discourse processing framework based on weighted abduction. We elaborate on ideas described in Hobbs et al. (1993) and implement the abductive inference procedure in a system called Mini-TACITUS. Particular attention is paid to constructing a large and reliable knowledge base for supporting inferences. For this purpose we exploit such lexical-semantic resources as WordNet and FrameNet. We test the proposed procedure and the obtained knowledge base on the Recognizing Textual Entailment task using the data sets from the RTE-2 challenge for evaluation. In addition, we provide an evaluation of the semantic role labeling produced by the system taking the Frame-Annotated Corpus for Textual Entailment as a gold standard.

In this paper, with the goal of using Viterbi algorithm as a quick Top-down parsing procedure, a ... more In this paper, with the goal of using Viterbi algorithm as a quick Top-down parsing procedure, a new probabilistic model called “Rule Bi-gram” is introduced. By extending rule bi-gram model, we have implemented a new parsing algorithm (VPA) based on the Viterbi algorithm. Our experiments show that although in applications in which an exact parse of the input sentence is required, this method may not be appropriate, in applications where speed is a crucial criterion (such as real-time speech recognition), the new algorithm performs very efficient and robust.