arXiv subjects

Jonathan K. Kummerfeld

Publications and source records attributed to Jonathan K. Kummerfeld.

At least 37 records · Page 2Linked to original sources

arXiv2021

Learning to Learn End-to-End Goal-Oriented Dialog From Related Dialog Tasks

For each goal-oriented dialog task of interest, large amounts of data need to be collected for end-to-end learning of a neural dialog system. Collecting that data is a costly and time-consuming process. Instead, we show that we can use only a small amount of data, supplemented with data from a related dialog task. Naively learning from related data fails to improve performance as the related data can be inconsistent with the target task. We describe a meta-learning based method that selectively learns from the related dialog task data. Our approach leads to significant accuracy improvements in an example dialog task.

cs.CL↗

arXiv2021

Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Health

Many statistical models have high accuracy on test benchmarks, but are not explainable, struggle in low-resource scenarios, cannot be reused for multiple tasks, and cannot easily integrate domain expertise. These factors limit their use, particularly in settings such as mental health, where it is difficult to annotate datasets and model outputs have significant impact. We introduce a micromodel architecture to address these challenges. Our approach allows researchers to build interpretable representations that embed domain knowledge and provide explanations throughout the model's decision process. We demonstrate the idea on multiple mental health tasks: depression classification, PTSD classification, and suicidal risk assessment. Our systems consistently produce strong results, even in low-resource scenarios, and are more interpretable than alternative methods.

cs.CL↗

arXiv2021

Analyzing the Surprising Variability in Word Embedding Stability Across Languages

Word embeddings are powerful representations that form the foundation of many natural language processing architectures, both in English and in other languages. To gain further insight into word embeddings, we explore their stability (e.g., overlap between the nearest neighbors of a word in different embedding spaces) in diverse languages. We discuss linguistic properties that are related to stability, drawing out insights about correlations with affixing, language gender systems, and other features. This has implications for embedding use, particularly in research that uses them to study language trends.

cs.CL↗

arXiv2021

Exploring Self-Identified Counseling Expertise in Online Support Forums

A growing number of people engage in online health forums, making it important to understand the quality of the advice they receive. In this paper, we explore the role of expertise in responses provided to help-seeking posts regarding mental health. We study the differences between (1) interactions with peers; and (2) interactions with self-identified mental health professionals. First, we show that a classifier can distinguish between these two groups, indicating that their language use does in fact differ. To understand this difference, we perform several analyses addressing engagement aspects, including whether their comments engage the support-seeker further as well as linguistic aspects, such as dominant language and linguistic style matching. Our work contributes toward the developing efforts of understanding how health experts engage with health information- and support-seekers in social networks. More broadly, it is a step toward a deeper understanding of the styles of interactions that cultivate supportive engagement in online communities.

cs.CL↗

arXiv2021

Quantifying and Avoiding Unfair Qualification Labour in Crowdsourcing

Extensive work has argued in favour of paying crowd workers a wage that is at least equivalent to the U.S. federal minimum wage. Meanwhile, research on collecting high quality annotations suggests using a qualification that requires workers to have previously completed a certain number of tasks. If most requesters who pay fairly require workers to have completed a large number of tasks already then workers need to complete a substantial amount of poorly paid work before they can earn a fair wage. Through analysis of worker discussions and guidance for researchers, we estimate that workers spend approximately 2.25 months of full time effort on poorly paid tasks in order to get the qualifications needed for better paid tasks. We discuss alternatives to this qualification and conduct a study of the correlation between qualifications and work quality on two NLP tasks. We find that it is possible to reduce the burden on workers while still collecting high quality data.

cs.CL↗

arXiv2021

Chord Embeddings: Analyzing What They Capture and Their Role for Next Chord Prediction and Artist Attribute Prediction

Natural language processing methods have been applied in a variety of music studies, drawing the connection between music and language. In this paper, we expand those approaches by investigating \textit{chord embeddings}, which we apply in two case studies to address two key questions: (1) what musical information do chord embeddings capture?; and (2) how might musical applications benefit from them? In our analysis, we show that they capture similarities between chords that adhere to important relationships described in music theory. In the first case study, we demonstrate that using chord embeddings in a next chord prediction task yields predictions that more closely match those by experienced musicians. In the second case study, we show the potential benefits of using the representations in tasks related to musical stylometrics.

cs.SD↗

arXiv2020

Exploring the Value of Personalized Word Embeddings

In this paper, we introduce personalized word embeddings, and examine their value for language modeling. We compare the performance of our proposed prediction model when using personalized versus generic word representations, and study how these representations can be leveraged for improved performance. We provide insight into what types of words can be more accurately predicted when building personalized models. Our results show that a subset of words belonging to specific psycholinguistic categories tend to vary more in their representations across users and that combining generic and personalized word embeddings yields the best performance, with a 4.7% relative reduction in perplexity. Additionally, we show that a language model using personalized word embeddings can be effectively used for authorship attribution.

cs.CL↗

arXiv2020

Compositional Demographic Word Embeddings

Word embeddings are usually derived from corpora containing text from many individuals, thus leading to general purpose representations rather than individually personalized representations. While personalized embeddings can be useful to improve language model performance and other language processing tasks, they can only be computed for people with a large amount of longitudinal data, which is not the case for new users. We propose a new form of personalized word embeddings that use demographic-specific word representations derived compositionally from full or partial demographic information for a user (i.e., gender, age, location, religion). We show that the resulting demographic-aware word representations outperform generic word representations on two tasks for English: language modeling and word associations. We further explore the trade-off between the number of available attributes and their relative effectiveness and discuss the ethical implications of using them.

cs.CL↗

arXiv2020

Improving Low Compute Language Modeling with In-Domain Embedding Initialisation

Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most language modeling research considers either a small dataset with a closed vocabulary (like the standard 1 million token Penn Treebank), or the whole web with byte-pair encoding. We show that for our target setting in English, initialising and freezing input embeddings using in-domain data can improve language model performance by providing a useful representation of rare words, and this pattern holds across several different domains. In the process, we show that the standard convention of tying input and output embeddings does not improve perplexity when initializing with embeddings trained on in-domain data.

cs.CL↗

arXiv2019

No Press Diplomacy: Modeling Multi-Agent Gameplay

Diplomacy is a seven-player non-stochastic, non-cooperative game, where agents acquire resources through a mix of teamwork and betrayal. Reliance on trust and coordination makes Diplomacy the first non-cooperative multi-agent benchmark for complex sequential social dilemmas in a rich environment. In this work, we focus on training an agent that learns to play the No Press version of Diplomacy where there is no dedicated communication channel between players. We present DipNet, a neural-network-based policy model for No Press Diplomacy. The model was trained on a new dataset of more than 150,000 human games. Our model is trained by supervised learning (SL) from expert trajectories, which is then used to initialize a reinforcement learning (RL) agent trained through self-play. Both the SL and RL agents demonstrate state-of-the-art No Press performance by beating popular rule-based bots.

cs.AI↗

arXiv2019

The Eighth Dialog System Technology Challenge

This paper introduces the Eighth Dialog System Technology Challenge. In line with recent challenges, the eighth edition focuses on applying end-to-end dialog technologies in a pragmatic way for multi-domain task-completion, noetic response selection, audio visual scene-aware dialog, and schema-guided dialog state tracking tasks. This paper describes the task definition, provided datasets, and evaluation set-up for each track. We also summarize the results of the submitted systems to highlight the overall trends of the state-of-the-art technologies for the tasks.

cs.CL↗

arXiv2019

An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction

Task-oriented dialog systems need to know when a query falls outside their range of supported intents, but current text classification corpora only define label sets that cover every example. We introduce a new dataset that includes queries that are out-of-scope---i.e., queries that do not fall into any of the system's supported intents. This poses a new challenge because models cannot assume that every query at inference time belongs to a system-supported intent class. Our dataset also covers 150 intent classes over 10 domains, capturing the breadth that a production task-oriented agent must handle. We evaluate a range of benchmark classifiers on our dataset along with several different out-of-scope identification schemes. We find that while the classifiers perform well on in-scope intent classification, they struggle to identify out-of-scope queries. Our dataset and evaluation fill an important gap in the field, offering a way of more rigorously and realistically benchmarking text classification in task-driven dialog systems.

cs.CL↗

arXiv2019

A Large-Scale Corpus for Conversation Disentanglement

Disentangling conversations mixed together in a single stream of messages is a difficult task, made harder by the lack of large manually annotated datasets. We created a new dataset of 77,563 messages manually annotated with reply-structure graphs that both disentangle conversations and define internal conversation structure. Our dataset is 16 times larger than all previously released datasets combined, the first to include adjudication of annotation disagreements, and the first to include context. We use our data to re-examine prior work, in particular, finding that 80% of conversations in a widely used dialogue corpus are either missing messages or contain extra messages. Our manually-annotated data presents an opportunity to develop robust data-driven methods for conversation disentanglement, which will help advance dialogue research.

cs.CL↗

arXiv2019

SLATE: A Super-Lightweight Annotation Tool for Experts

Many annotation tools have been developed, covering a wide variety of tasks and providing features like user management, pre-processing, and automatic labeling. However, all of these tools use Graphical User Interfaces, and often require substantial effort to install and configure. This paper presents a new annotation tool that is designed to fill the niche of a lightweight interface for users with a terminal-based workflow. Slate supports annotation at different scales (spans of characters, tokens, and lines, or a document) and of different types (free text, labels, and links), with easily customisable keybindings, and unicode support. In a user study comparing with other tools it was consistently the easiest to install and use. Slate fills a need not met by existing systems, and has already been used to annotate two corpora, one of which involved over 250 hours of annotation effort.

cs.CL↗

arXiv2019

Look Who's Talking: Inferring Speaker Attributes from Personal Longitudinal Dialog

We examine a large dialog corpus obtained from the conversation history of a single individual with 104 conversation partners. The corpus consists of half a million instant messages, across several messaging platforms. We focus our analyses on seven speaker attributes, each of which partitions the set of speakers, namely: gender; relative age; family member; romantic partner; classmate; co-worker; and native to the same country. In addition to the content of the messages, we examine conversational aspects such as the time messages are sent, messaging frequency, psycholinguistic word categories, linguistic mirroring, and graph-based features reflecting how people in the corpus mention each other. We present two sets of experiments predicting each attribute using (1) short context windows; and (2) a larger set of messages. We find that using all features leads to gains of 9-14% over using message text only.

cs.CL↗

arXiv2019

Outlier Detection for Improved Data Quality and Diversity in Dialog Systems

In a corpus of data, outliers are either errors: mistakes in the data that are counterproductive, or are unique: informative samples that improve model robustness. Identifying outliers can lead to better datasets by (1) removing noise in datasets and (2) guiding collection of additional data to fill gaps. However, the problem of detecting both outlier types has received relatively little attention in NLP, particularly for dialog systems. We introduce a simple and effective technique for detecting both erroneous and unique samples in a corpus of short texts using neural sentence embeddings combined with distance-based outlier detection. We also present a novel data collection pipeline built atop our detection technique to automatically and iteratively mine unique data samples while discarding erroneous samples. Experiments show that our outlier detection technique is effective at finding errors while our data collection pipeline yields highly diverse corpora that in turn produce more robust intent classification and slot-filling models.

cs.CL↗

arXiv2019

Dialog System Technology Challenge 7

This paper introduces the Seventh Dialog System Technology Challenges (DSTC), which use shared datasets to explore the problem of building dialog systems. Recently, end-to-end dialog modeling approaches have been applied to various dialog tasks. The seventh DSTC (DSTC7) focuses on developing technologies related to end-to-end dialog systems for (1) sentence selection, (2) sentence generation and (3) audio visual scene aware dialog. This paper summarizes the overall setup and results of DSTC7, including detailed descriptions of the different tracks and provided datasets. We also describe overall trends in the submitted systems and the key results. Each track introduced new datasets and participants achieved impressive results using state-of-the-art end-to-end technologies.

cs.CL↗

arXiv2018

Improving Text-to-SQL Evaluation Methodology

To be informative, an evaluation must measure how well systems generalize to realistic unseen data. We identify limitations of and propose improvements to current evaluations of text-to-SQL systems. First, we compare human-generated and automatically generated questions, characterizing properties of queries necessary for real-world applications. To facilitate evaluation on multiple datasets, we release standardized and improved versions of seven existing datasets and one new text-to-SQL dataset. Second, we show that the current division of data into training and test sets measures robustness to variations in the way questions are asked, but only partially tests how well systems generalize to new queries; therefore, we propose a complementary dataset split for evaluation of future work. Finally, we demonstrate how the common practice of anonymizing variables during evaluation removes an important challenge of the task. Our observations highlight key difficulties, and our methodology enables effective measurement of future development.

cs.CL↗