The Switchboard-1 Telephone Speech Corpus (LDC97S62) consists of approximately 260 hours of speech and was originally collected by Texas Instruments in 1990-1, under DARPA sponsorship. The first release of the corpus was published by NIST and distributed by the LDC in 1992-3. Switchboard is a collection of about 2,400 two-sided telephone conversations among 543 speakers (302 male, 241 female) from all areas of the United States. A computer-driven robot operator system handled the calls, giving the caller appropriate recorded prompts, selecting and dialing another person (the callee) to take part in a conversation, introducing a topic for discussion and recording the speech from the two subjects into separate channels until the conversation was finished. About 70 topics were provided, of which about 50 were used frequently. Selection of topics and callees was constrained so that: (1) no two speakers would converse together more than once and (2) no one spoke more than once on a given topic. Source: https://catalog.ldc.upenn.edu/LDC97S62
FaithDial is a new benchmark for hallucination-free dialogues, by editing hallucinated responses in the Wizard of Wikipedia (WoW) benchmark. FaithDial contains around 50K turns across 5.5K conversations. If trained on FaithDial, state-of-the-art dialogue models are significantly more faithful while also enhancing other dialogue aspects like cooperativeness, creativity and engagement.
This is a document grounded dataset for text conversations. "Document Grounded Conversations" are conversations that are about the contents of a specified document. In this dataset the specified documents are Wikipedia articles about popular movies. The dataset contains 4112 conversations with an average of 21.43 turns per conversation. Source: https://github.com/festvox/datasets-CMU_DoG Image Source: https://arxiv.org/pdf/1809.07358v1.pdf
We construct a dataset named CPED from 40 Chinese TV shows. CPED consists of multisource knowledge related to empathy and personal characteristic. This knowledge covers 13 emotions, gender, Big Five personality traits, 19 dialogue acts and other knowledge. * We build a multiturn Chinese Personalized and Emotional Dialogue dataset called CPED. To the best of our knowledge, CPED is the first Chinese personalized and emotional dialogue dataset. CPED contains 12K dialogues and 133K utterances with multi-modal context. Therefore, it can be used in both complicated dialogue understanding and human-like conversation generation. * CPED has been annotated with 3 character attributes (name, gender age), Big Five personality traits, 2 types of dynamic emotional information (sentiment and emotion) and DAs. The personality traits and emotions can be used as prior external knowledge for open-domain conversation generation, making the conversation system have a good command of personification capabilities. * We propose three tasks for CPED: personality recognition in conversations (PRC), emotion recognition in conversations (ERC), and personalized and emotional conversation (PEC). A set of experiments verify the importance of using personalities and emotions as prior external knowledge for conversation generation.
HINT3 is a dataset for intent detection. It consists of 3 different datasets each containing a diverse set of intents in a single domain - mattress products retail, fitness supplements retail and online gaming named SOFMattress, Curekart and Powerplay11. Source: https://github.com/hellohaptik/HINT3
PersonalDialog is a large-scale multi-turn dialogue dataset containing various traits from a large number of speakers. The dataset consists of 20.83M sessions and 56.25M utterances from 8.47M speakers. Each utterance is associated with a speaker who is marked with traits like Age, Gender, Location, Interest Tags, etc. Several anonymization schemes are designed to protect the privacy of each speaker. Source: Personalized Dialogue Generation with Diversified Traits Image Source: https://arxiv.org/pdf/1901.09672v2.pdf
Most existing dialogue systems fail to respond properly to potentially unsafe user utterances by either ignoring or passively agreeing with them. To address this issue, we introduce ProsocialDialog, the first large-scale multi-turn dialogue dataset to teach conversational agents to respond to problematic content following social norms. Covering diverse unethical, problematic, biased, and toxic situations, ProsocialDialog contains responses that encourage prosocial behavior, grounded in commonsense social rules (i.e., rules-of-thumb, RoTs). ProsocialDialog consists of 58K dialogues between a speaker showing potentially unsafe behavior and a speaker giving constructive feedback for more socially acceptable behavior. Specifically, it contains a rich suite of: * 331K utterances * 160K Rules-of-thumb (RoTs) * 497K dialogue safety labels accompanied by free-form rationales
Next generation task-oriented dialog systems need to understand conversational contexts with their perceived surroundings, to effectively help users in the real-world multimodal environment. Existing task-oriented dialog datasets aimed towards virtual assistance fall short and do not situate the dialog in the user's multimodal context. To overcome, we present a new dataset for Situated and Interactive Multimodal Conversations, SIMMC 2.0, which includes 11K task-oriented user<->assistant dialogs (117K utterances) in the shopping domain, grounded in immersive and photo-realistic scenes. The dialogs are collected using a two-phase pipeline: (1) A novel multimodal dialog simulator generates simulated dialog flows, with an emphasis on diversity and richness of interactions, (2) Manual paraphrasing of the generated utterances to collect diverse referring expressions. We provide an in-depth analysis of the collected dataset, and describe in detail the four main benchmark tasks we propose. Our baseline model, powered by the state-of-the-art language model, shows promising results, and highlights new challenges and directions for the community to study.
A large-scale collection of visually-grounded, task-oriented dialogues in English designed to investigate shared dialogue history accumulating during conversation. Source: The PhotoBook Dataset: Building Common Ground through Visually-Grounded Dialogue
VoxForge is an open speech dataset that was set up to collect transcribed speech for use with Free and Open Source Speech Recognition Engines (on Linux, Windows and Mac). Image Source: http://www.voxforge.org/home
Action-Based Conversations Dataset (ABCD) is a goal-oriented dialogue fully-labeled dataset with over 10K human-to-human dialogues containing 55 distinct user intents requiring unique sequences of actions constrained by policies to achieve task success. The dataset is proposed to study customer service dialogue systems in more realistic settings.
CLEVR-Dialog is a large diagnostic dataset for studying multi-round reasoning in visual dialog. Specifically, that authors construct a dialog grammar that is grounded in the scene graphs of the images from the CLEVR dataset. This combination results in a dataset where all aspects of the visual dialog are fully annotated. In total, CLEVR-Dialog contains 5 instances of 10-round dialogs for about 85k CLEVR images, totaling to 4.25M question-answer pairs. The CLEVR-Dialog is used to benchmark performance of standard visual dialog models; in particular, on visual coreference resolution (as a function of the coreference distance). This is the first analysis of its kind for visual dialog models that was not possible without this dataset. CLEVR-Dialog is aims to help inform the development of future models for visual dialog. Source: CLEVR-Dialog
BiToD is a bilingual multi-domain dataset for end-to-end task-oriented dialogue modeling. BiToD contains over 7k multi-domain dialogues (144k utterances) with a large and realistic bilingual knowledge base. It serves as an effective benchmark for evaluating bilingual ToD systems and cross-lingual transfer learning approaches.
KaMed is a knowledge-aware medical dialogue dataset, which contains over 60,000 medical dialogue sessions with 5,682 entities (such as Asthma and Atropine).
The MRDA corpus consists of about 75 hours of speech from 75 naturally-occurring meetings among 53 speakers. The tagset used for labeling is a modified version of the SWBD-DAMSL tagset. It is annotated with three types of information: marking of the dialogue act segment boundaries, marking of the dialogue acts and marking of correspondences between dialogue acts. Description from NLP Progress
OpenViDial is a large-scale open-domain dialogue dataset with visual contexts. The dialogue turns and visual contexts are extracted from movies and TV series, where each dialogue turn is paired with the corresponding visual context in which it takes place. OpenViDial contains a total number of 1.1 million dialogue turns, and thus 1.1 million visual contexts stored in images. Source: https://github.com/ShannonAI/OpenViDial Image Source: https://github.com/ShannonAI/OpenViDial
The SmartLights benchmark from Snipstests the capability of controlling lights in different rooms. It consists of 1660 requests which are split into five partitions for a 5-fold evaluation. A sample command could be: “please change the [bedroom] lights to [red]” or “i’d like the [living room] lights to be at [twelve] percent”
In MutualFriends, two agents, A and B, each have a private knowledge base, which contains a list of friends with multiple attributes (e.g., name, school, major, etc.). The agents must chat with each other to find their unique mutual friend. Source: Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings
FusedChat is an inter-mode dialogue dataset. It contains dialogue sessions fusing task-oriented dialogues (TOD) and open-domain dialogues (ODD). Based on MultiWOZ, FusedChat appends or prepends an ODD to every existing TOD. See more details in the paper.
OTTers is a dataset of human one-turn topic transitions. In this task, models must connect two topics in a cooperative and coherent manner, by generating a "bridging" utterance connecting the new topic tot he topic of the previous conversation turn.
ClovaCall is a new large-scale Korean call-based speech corpus under a goal-oriented dialog scenario from more than 11,000 people. The raw dataset of ClovaCall includes approximately 112,000 pairs of a short sentence and its corresponding spoken utterance in a restaurant reservation domain. Source: https://github.com/ClovaAI/ClovaCall
A large scale Chinese multi-modal dialogue corpus (120.84K dialogues and 198.82 K images). - MMCHAT contains image-grounded dialogues collected from real conversations on social media. - We manually annotate 100K dialogues from MMCHAT with the dialogue quality and whether the dialogues are related to the given image. - We provide the rule-filtered raw dialogues that are used to create MMChat (Rule Filtered Raw MMChat). It contains 4.257 M dialogue sessions and 4.874 M images - We provide a version of MMChat that is filtered based on LCCC (LCCC Filtered MMChat). This version contain much cleaner dialogues (492.6 K dialogue sessions and 1.066 M images)
RiSAWOZ is a large-scale multi-domain Chinese Wizard-of-Oz dataset with Rich Semantic Annotations. RiSAWOZ contains 11.2K human-to-human (H2H) multi-turn semantically annotated dialogues, with more than 150K utterances spanning over 12 domains, which is larger than all previous annotated H2H conversational datasets. Both single- and multi-domain dialogues are constructed, accounting for 65% and 35%, respectively. Each dialogue is labelled with comprehensive dialogue annotations, including dialogue goal in the form of natural language description, domain, dialogue states and acts at both the user and system side. In addition to traditional dialogue annotations, it also includes linguistic annotations on discourse phenomena, e.g., ellipsis and coreference, in dialogues, which are useful for dialogue coreference and ellipsis resolution tasks. Source: https://github.com/terryqj0107/RiSAWOZ
Timers and Such is an open source dataset of spoken English commands for common voice control use cases involving numbers. The dataset has four intents, corresponding to four common offline voice assistant uses: SetTimer, SetAlarm, SimpleMath, and UnitConversion. The semantic label for each utterance is a dictionary with the intent and a number of slots. All recordings were converted from their original formats to single-channel 16,000 Hz .wav files.
A Game Of Sorts is a collaborative image ranking task. Players are asked to rank a set of images based on a given sorting criterion. The game provides a framework for the evaluation of visually grounded language understanding and generation of referring expressions in multimodal dialogue settings.
DiaASQ is a fine-grained Aspect-based Sentiment Analysis (ABSA) benchmark under the conversation scenario. It challenges existing ABSA methods by 1) extracting quadruple of target-aspect-opinion-sentiment in a dialogue, and 2) modeling the dialogue discourse structures. The dataset is constructed by systematically crawling tweets from digital bloggers, followed by a series of preprocessing steps including filtering, normalizing, pruning, and annotating the collected dialogues, resulting in a final corpus of 1,000 dialogues. To enhance the multilingual usability, DiaASQ has both the English and Chinese versions of languages.
Collected by leveraging background knowledge from a larger, more highly represented dialogue source. Source: Few-Shot Dialogue Generation Without Annotated Data: A Transfer Learning Approach
The Situated Corpus Of Understanding Transactions (SCOUT) is a multi-modal collection of human-robot dialogue in the task domain of collaborative exploration. The corpus was constructed from multi-phased Wizard-of-Oz experiments where human participants gave verbal instructions to a remotely-located robot to move and gather information about its surroundings. Each dialogue involved a human Commander, a Dialogue Manager (DM), and a Robot Navigator (RN), and took place in physical or simulated environments. SCOUT contains Transcripts of human-robot dialogues, aligned with the Images taken by the robot at the request of the Commander. The transcripts have been annotated with Dialogue Structure, including Transcaction Units (TUs), Antecedents, and Relations. A subset of utterances have been annotated with Dialogue Semantics including Standard-AMR and Dialogue-AMR. A subset of the Maps have been curated that depict the LIDAR Maps at the end of the dialogue and have been annotated as Exploration Maps.
DeliData is the first publicly available dataset containing collaborative conversations on solving a cognitive task, consisting of 500 group dialogues and 14k utterances. Source: DeliData: A dataset for deliberation in multi-party problem solving Image source: https://www.delibot.xyz/#
Emotional Dialogue Acts data contains dialogue act labels for existing emotion multi-modal conversational datasets. We chose two popular multimodal emotion datasets: Multimodal EmotionLines Dataset (MELD) and Interactive Emotional dyadic MOtion CAPture database (IEMOCAP). EDAs reveal associations between dialogue acts and emotional states in a natural-conversational language such as Accept/Agree dialogue acts often occur with the Joy emotion, Apology with Sadness, and Thanking with Joy.