---
library_name: salescue
pipeline_tag: text-classification
language:
- en
base_model: microsoft/deberta-v3-base
tags:
- sales
- salescue
- sentiment
- sales-intelligence
- b2b
- pytorch
license: mit
---

# SalesCue — sentiment

DisentangledSentimentIntentHead module from the
[SalesCue](https://github.com/v9ai/ai-apps) sales intelligence library.

> **Status**: `untrained` — architecture only, random initialization. Use as a starting point for fine-tuning.

## Research Contribution

**MI-Minimized Sentiment-Intent Disentanglement**

Sentiment and intent are entangled in text representations. DisentangledSentimentIntentHead enforces disentanglement explicitly: the sentiment representation contains zero information about intent, and vice versa. Uses *mutual information minimization* via the CLUB bound (Cheng et al., 2020) to provably decorrelate the two representations, then learns inversion patterns from their interaction.

## Usage

```python
from salescue import SalesCueModel

model = SalesCueModel.from_pretrained("v9ai/salescue-sentiment-v1")
result = model.predict("your sales text here")
print(result)
```

## Labels

- `enthusiastic`
- `positive_engaged`
- `neutral_professional`
- `cautious_interest`
- `polite_decline`
- `frustrated_objection`
- `hostile_rejection`

## Architecture

- **Backbone**: [`microsoft/deberta-v3-base`](https://huggingface.co/microsoft/deberta-v3-base) (shared encoder, 768-dim)
- **Head**: `DisentangledSentimentIntentHead`
- **Parameters**: head only (backbone loaded separately)

## Intended Use

- **Primary**: B2B sales intelligence — lead scoring, email analysis, conversation insights
- **Users**: Sales teams, RevOps, GTM engineers building sales automation
- **Input**: English sales text (emails, call transcripts, prospect communications)

## Limitations

- **Untrained weights**: This release contains the architecture only. Weights are randomly initialized and must be fine-tuned on domain-specific data before production use.
- **English only**: Designed for English sales text. Performance on other languages is untested.
- **Domain-specific**: Optimized for B2B sales communications. May not generalize to other text domains.
- **Shared backbone**: Requires `microsoft/deberta-v3-base` loaded via the SalesCue library.

## About SalesCue

SalesCue is a sales intelligence library with 12 ML modules sharing a single
DeBERTa-v3-base encoder backbone. Modules can be composed via Unix-style piping:

```python
from salescue import Document
result = Document("interested in pricing") | ai.score | ai.intent | ai.sentiment
```

All modules: `score` `intent` `reply` `triggers` `icp` `objection` `sentiment` `spam` `entities` `call` `subject` `emailgen`

See the [SalesCue documentation](https://github.com/v9ai/ai-apps) for details.